everything-claude-code

fix: harden windows observer prompt handling

Affaan Mustafa · 2026-04-06 14:05:38 -07:00

df96abe74c

fix: raise observer turn budget

Affaan Mustafa · 2026-04-05 14:23:06 -07:00

908116d736

fix: clean up observer sessions on lifecycle end

Affaan Mustafa · 2026-04-02 18:02:29 -07:00

16e9b17ad7

fix: add POSIX fallback for observer lazy-start

Affaan Mustafa · 2026-04-02 17:07:32 -07:00

70be8f9f44

fix(clv2): resolve cwd to git root before project detection

Affaan Mustafa · 2026-03-30 04:46:31 -04:00

3f6a14acde

fix(clv2): honor CLV2_CONFIG in start-observer

Affaan Mustafa · 2026-03-29 00:21:55 -04:00

be76918850

fix(observer): clean up prompt_file early and fix test for analysis_relpath

- Remove prompt_file immediately after shell expansion into -p arg,
  avoiding stale temp files during long analysis windows (greptile feedback)
- Update test assertion to check analysis_relpath instead of analysis_file,
  matching the cross-platform relative path change from earlier commits

Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>

Lidang-Jiang · 2026-03-28 23:32:44 +08:00

7a4cb8c570

fix(observer): clean up temp files on cd failure early return

The cd "$PROJECT_DIR" failure path returned without removing prompt_file
and analysis_file, leaving stale temp files in .observer-tmp/.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>

Lidang-Jiang · 2026-03-28 11:38:10 +08:00

451732164f

fix(observer): guard cd failure with early return and log message

Address reviewer feedback: under set +e, a failing cd would silently
leave CWD unchanged, causing the relative analysis path to break.
Add || return with a diagnostic log entry.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>

Lidang-Jiang · 2026-03-28 10:45:41 +08:00

194bc0000b

fix(observer): anchor CWD to PROJECT_DIR before Claude invocation

Reviewers correctly identified that the relative analysis_relpath
(.observer-tmp/<file>) only resolves when CWD equals PROJECT_DIR.
Without an explicit cd, non-Windows users launching the observer from
a different directory would fail to read the analysis file.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>

Lidang-Jiang · 2026-03-28 10:34:40 +08:00

31af1adcc8

fix(observer): improve Windows compatibility for temp files and Haiku prompt

Address remaining issues from #842 after PR #903 moved temp files to
PROJECT_DIR/.observer-tmp:

Bug A (path resolution): Use relative paths (.observer-tmp/filename)
in the prompt instead of absolute paths from mktemp. On Windows
Git Bash/MSYS2, absolute paths use MSYS-style prefixes (/c/Users/...)
that the spawned Claude subprocess may fail to resolve.

Bug B (asks for permission): Add explicit IMPORTANT instruction block
at the prompt start telling the Haiku agent it is in non-interactive
--print mode and must use the Write tool directly without asking for
confirmation.

Additional improvements:
- Pass prompt via -p flag instead of stdin redirect for Windows compat
- Add .observer-tmp/ to .gitignore to prevent accidental commits

Fixes #842

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

Signed-off-by: Lidang-Jiang <lidangjiang@gmail.com>

Lidang-Jiang · 2026-03-28 09:54:35 +08:00

c80631fc1d

fix: fold session manager blockers into one candidate

Affaan Mustafa · 2026-03-24 23:08:27 -04:00

1d0aa5ac2a

feat: pending instinct TTL pruning and /prune command (#725 )

* feat: add pending instinct TTL pruning and /prune command

Pending instincts generated by the observer accumulate indefinitely
with no cleanup mechanism. This adds lifecycle management:

- `instinct-cli.py prune` — delete pending instincts older than 30 days
  (configurable via --max-age). Supports --dry-run and --quiet flags.
- Enhanced `status` command — shows pending count, warns at 5+,
  highlights instincts expiring within 7 days.
- `observer-loop.sh` — runs prune before each analysis cycle.
- `/prune` slash command — user-facing command for manual pruning.

Design rationale: council consensus (4/4) rejected auto-promote in
favor of TTL-based garbage collection. Frequency of observation does
not establish correctness. Unreviewed pending instincts auto-delete
after 30 days; if the pattern is real, the observer will regenerate it.

Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>

* fix: remove duplicate functions, broaden extension filter, fix prune output

- Remove duplicate _collect_pending_dirs and _parse_created_date defs
- Use ALLOWED_INSTINCT_EXTENSIONS (.md/.yaml/.yml) instead of .md-only
- Track actually-deleted items separately from expired for accurate output
- Update README.md and AGENTS.md command counts: 59 → 60

Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>

* fix: address Copilot and CodeRabbit review findings

- Use is_dir() instead of exists() for pending path checks
- Change > to >= for --max-age boundary (--max-age 0 now prunes all)
- Use CLV2_PYTHON_CMD env var in observer-loop.sh prune call
- Remove unused source_dupes variable
- Remove extraneous f-string prefix on static string

Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>

* fix: update AGENTS.md project structure command count 59 → 60

Co-Authored-By: Claude <noreply@anthropic.com>

* fix: address cubic and coderabbit review findings

- Fix status early return skipping pending instinct warnings (cubic #1)
- Exclude already-expired items from expiring-soon filter (cubic #2)
- Warn on unparseable pending instinct age instead of silent skip (cubic #4)
- Log prune failures to observer.log instead of silencing (cubic #5)

Co-Authored-By: Claude <noreply@anthropic.com>

* fix: YAML single-quote unescaping, f-string cleanup, add /prune to README

- Fix single-quoted YAML unescaping: use '' doubling (YAML spec) not
  backslash escaping which only applies to double-quoted strings (greptile P1)
- Remove extraneous f-string prefix on static string (coderabbit)
- Add /prune to README command catalog and file tree (cubic)

Co-Authored-By: Claude <noreply@anthropic.com>

---------

Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Happy <yesreply@happy.engineering>

Chris Yau · 2026-03-22 15:40:58 -07:00

0e733753e0

security: remove supply chain risks, external promotions, and unauthorized credits

- Remove zenith.chat references and @DRodriguezFX shoutout from README
- Remove Inspiration Credits section (already in CHANGELOG.md)
- Remove awesome-agent-skills reference from Links
- Remove Plankton H3 section by @alxfazio (skill stays in skills/)
- Remove brand names (InsAIts, VideoDB, Evos) from v1.9.0 notes
- Remove @ericcai0814 individual credit from README (kept in CHANGELOG)
- Add Security Guide to Links section
- Replace curl-pipe-to-bash in autonomous-loops with review warning
- Replace git clone in plankton-code-quality with review warning
- Replace pip install git+ in agent-eval with review warning
- Replace npm install -g in dmux-workflows with review warning
- Add commercial API notice to nutrient-document-processing
- Remove VideoDB maintainer credit from videodb skill
- Replace skill-creator.app link with ECC-Tools GitHub App reference

Affaan Mustafa · 2026-03-21 18:10:05 -07:00

6b2de1baff

Merge pull request #664 from ymdvsymd/fix/observer-sandbox-access-661

fix(clv2): add --allowedTools to observer Haiku invocation (#661)

Affaan Mustafa · 2026-03-20 00:16:42 -07:00

a6bd90713d

fix(clv2): use -e instead of -d for .git check in detect-project.sh

In git worktrees, .git is a file (not a directory) containing a gitdir
pointer. The -d test fails for worktree checkouts, causing project
detection to fall through to the "global" fallback. Changing to -e
(exists) handles both regular repos and worktrees correctly.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

to.watanabe · 2026-03-20 16:02:10 +09:00

04f8675624

fix(clv2): add --allowedTools to observer Haiku invocation (#661 )

The observer's Haiku subprocess cannot access files outside the project
sandbox (/tmp/ for observations, ~/.claude/homunculus/ for instincts).
Adding --allowedTools "Read,Write" grants the necessary file access
while keeping the subprocess constrained by --max-turns and timeout.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

to.watanabe · 2026-03-20 16:00:17 +09:00

f37c92cfe2

fix(observe): allow sdk-ts entrypoint in observation hook (#614 )

Clean surgical fix allowing sdk-ts entrypoint in observe hook for Agent SDK sessions. Has APPROVED review.

Chris Yau · 2026-03-19 20:49:15 -07:00

a9edf54d2f

fix: observer memory explosion with throttling, re-entrancy guard, and tail sampling (#536 )

Three fixes for the positive feedback loop causing runaway memory usage:

1. SIGUSR1 throttling in observe.sh: Signal observer only every 20
   observations (configurable via ECC_OBSERVER_SIGNAL_EVERY_N) instead
   of on every tool call. Uses a counter file to track invocations.

2. Re-entrancy guard in observer-loop.sh on_usr1(): ANALYZING flag
   prevents parallel Claude analysis processes from spawning when
   signals arrive while analysis is already running.

3. Cooldown + tail-based sampling in observer-loop.sh:
   - 60s cooldown between analyses (ECC_OBSERVER_ANALYSIS_COOLDOWN)
   - Only last 500 lines sent to LLM (ECC_OBSERVER_MAX_ANALYSIS_LINES)
     instead of the entire observations file

Closes #521

Affaan Mustafa · 2026-03-16 13:47:25 -07:00

f9e8287346

fix(continuous-learning-v2): add lazy-start observer logic (#508 )

* feat(continuous-learning-v2): add lazy-start observer logic

Auto-starts observer when observer.enabled: true in config and no .observer.pid exists.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(continuous-learning-v2): address PR review concerns

- Use flock for atomic check-then-act to prevent race conditions
- Check both project-scoped AND global PID files before starting
- Support CLV2_CONFIG override for config file path
- Check disabled file in lazy-start logic
- Use double-check pattern after acquiring lock

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(observe.sh): address PR review comments

- Add stale PID cleanup via _CHECK_OBSERVER_RUNNING function
- Add macOS fallback using lockfile when flock unavailable
- Fix CLV2_CONFIG override: use EFFECTIVE_CONFIG for both check and read
- Use proper Python context manager (with open() as f)
- Deduplicate signaled PIDs to avoid duplicate USR1 signals

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(observe.sh): wrap macOS lockfile fallback in subshell with trap

- Wrap lockfile block in subshell so exit 0 only terminates that block
- Add trap for EXIT to clean up lock file on script interruption
- Add -l 30 (30 second expiry) to prevent permanent lock file stuck

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(observe.sh): address remaining PR review comments

- Validate PID is a positive integer before kill calls to prevent
  signaling invalid targets (e.g. -1 could signal all processes)
- Pass config path via env var instead of interpolating shell variable
  into Python -c string to prevent injection/breakage on special paths
- Check CLV2_CONFIG-derived directory for disabled file so disable
  guard respects the same config source as lazy-start

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

Albert Lie 이영덕 · 2026-03-16 13:38:20 -07:00

b57b573085

fix: harden observer hooks and test discovery (#513 )

Affaan Mustafa · 2026-03-15 21:47:15 -07:00

8878c6d6b0

merge: dmux worktree (selective install, orchestration, observer fixes)

Affaan Mustafa · 2026-03-14 12:55:56 -07:00

fcaf78e449

feat: orchestration harness, selective install, observer improvements

Affaan Mustafa · 2026-03-14 12:55:25 -07:00

4e028bd2d2

fix: harden observe loop prevention

Affaan Mustafa · 2026-03-13 01:16:45 -07:00

5e481879ca

Merge branch 'main' into main

Affaan Mustafa · 2026-03-13 00:00:34 -07:00

1c1a9ef73e

fix: harden observer prompt guard handling

Affaan Mustafa · 2026-03-12 23:59:01 -07:00

e043a2824a

feat: active hours + idle detection gates for session-guardian (#413 )

* feat: add project cooldown log to prevent rapid observer re-spawn

Adds session-guardian.sh, called by observer-loop.sh before each Haiku
spawn. It reads ~/.claude/observer-last-run.log and blocks the cycle if
the same project was observed within OBSERVER_INTERVAL_SECONDS (default
300s).

Prevents self-referential loops where a spawned session triggers
observe.sh, which signals the observer before the cooldown has elapsed.

Uses a mkdir-based lock for safe concurrent access across multiple
simultaneously-observed projects. Log entries use tab-delimited format
to handle paths containing spaces. Fails open on lock contention.

Config:
  OBSERVER_INTERVAL_SECONDS   default: 300
  OBSERVER_LAST_RUN_LOG       default: ~/.claude/observer-last-run.log

No external dependencies. Works on macOS, Linux, Windows (Git Bash/MSYS2).

* feat: extend session-guardian with time window and idle detection gates

Adds Gate 1 (active hours check) and Gate 3 (system idle detection) to
session-guardian.sh, building on the per-project cooldown log from PR 1.

Gate 1 — Time Window:
- OBSERVER_ACTIVE_HOURS_START/END (default 800–2300 local time)
- Uses date +%k%M with 10# prefix to avoid octal crash at midnight
- Toolless on all platforms; set both vars to 0 to disable

Gate 3 — Idle Detection:
- macOS: ioreg + awk (built-in, no deps)
- Linux: xprintidle if available, else fail open
- Windows (Git Bash/MSYS2): PowerShell GetLastInputInfo via Add-Type
- Unknown/headless: always returns 0 (fail open)
- OBSERVER_MAX_IDLE_SECONDS=0 disables gate

Fixes in this commit:
- 10# base-10 prefix prevents octal arithmetic crash on midnight minutes
  containing digits 8 or 9 (e.g. 00:08 = "008" is invalid octal)
- PowerShell output piped through tr -d '\r' to strip Windows CRLF;
  also uses [long] cast to avoid TickCount 32-bit overflow after 24 days
- mktemp now uses log file directory instead of TMPDIR to ensure
  same-filesystem mv on Linux (atomic rename instead of copy+unlink)
- mkdir -p failure exits 0 (fail open) rather than crashing under set -e
- Numeric validation on last_spawn prevents arithmetic error on corrupt log

Gate execution order: 1 (time, ~0ms) → 2 (cooldown, ~1ms) → 3 (idle, ~50ms)

* fix: harden session guardian gates

---------

Co-authored-by: Affaan Mustafa <affaan@dcube.ai>

ispaydeu · 2026-03-12 23:44:34 -07:00

a6f380fde0

fix(observe): 5-layer automated session guard to prevent self-loop observations (#399 )

* fix(observe): add 5-layer automated session guard to prevent self-loop observations

observe.sh currently fires for ALL hook events including automated/programmatic
sessions: the ECC observer's own Haiku analysis runs, claude-mem observer
sessions, CI pipelines, and any other tool that spawns `claude --print`.

This causes an infinite feedback loop where automated sessions generate
observations that trigger more automated analysis, burning Haiku tokens with
no human activity.

Add a 5-layer guard block after the `disabled` check:

Layer 1: agent_id payload field — only present in subagent hooks; skip any
         subagent-scoped session (always automated by definition).

Layer 2: CLAUDE_CODE_ENTRYPOINT env var — Claude Code sets this to sdk-ts,
         sdk-py, sdk-cli, mcp, or remote for programmatic/SDK invocations.
         Skip if any non-cli entrypoint is detected. This is universal: catches
         any tool using the Anthropic SDK without requiring tool cooperation.

Layer 3: ECC_HOOK_PROFILE=minimal — existing ECC mechanism; respect it here
         to suppress non-essential hooks in observer contexts.

Layer 4: ECC_SKIP_OBSERVE=1 — cooperative env var any external tool can set
         before spawning automated sessions (explicit opt-out contract).

Layer 5: CWD path exclusions — skip sessions whose working directory matches
         known observer-session path patterns. Configurable via
         ECC_OBSERVE_SKIP_PATHS (comma-separated substrings, default:
         "observer-sessions,.claude-mem").

Also fix observer-loop.sh to set ECC_SKIP_OBSERVE=1 and ECC_HOOK_PROFILE=minimal
before spawning the Haiku analysis subprocess, making the observer loop
self-aware and closing the ECC→ECC self-observation loop without needing
external coordination.

Fixes: observe.sh fires unconditionally on automated sessions (#398)

* fix(observe): address review feedback — reorder guards cheapest-first, fix empty pattern bug

Two issues flagged by Copilot and CodeRabbit in PR #399:

1. Layer ordering: the agent_id check spawns a Python subprocess but ran
   before the cheap env-var checks (CLAUDE_CODE_ENTRYPOINT, ECC_HOOK_PROFILE,
   ECC_SKIP_OBSERVE). Reorder to put all env-var checks first (Layers 1-3),
   then the subprocess-requiring agent_id check (Layer 4). Automated sessions
   that set env vars — the common case — now exit without spawning Python.

2. Empty pattern bug in Layer 5: if ECC_OBSERVE_SKIP_PATHS contains a trailing
   comma or spaces after commas (e.g. "path1, path2" or "path1,"), _pattern
   becomes empty or whitespace-only, and the glob *""* matches every CWD,
   silently disabling all observations. Fix: trim leading/trailing whitespace
   from each pattern and skip empty patterns with `continue`.

* fix: fail closed for non-cli entrypoints

---------

Co-authored-by: Affaan Mustafa <affaan@dcube.ai>

ispaydeu · 2026-03-12 23:40:03 -07:00

c52a28ace9

fix: add confirmation-prompt guard to start-observer.sh (issue #400 )

- Redirect observer output to temp log before appending to main log
- Check temp log for confirmation/permission language immediately after start
- Fail closed with exit 2 if detected, preventing retry loops

swarnika-cmd · 2026-03-12 06:52:54 +05:30

96708e5d45

fix: observer fails closed on confirmation/permission prompts (issue #400 )

swarnika-cmd · 2026-03-12 06:46:42 +05:30

8079d354d1

fix: repair opencode config and project metadata

Affaan Mustafa · 2026-03-11 01:52:10 -07:00

da4db99c94

fix: raise observer analysis turn budget

Affaan Mustafa · 2026-03-10 20:52:53 -07:00

16bc7436c5

fix: handle null tool_response fallback

Affaan Mustafa · 2026-03-10 19:14:56 -07:00

4de776341e

fix: read tool_response field in observe.sh (#377 )

Claude Code sends tool output as `tool_response` in PostToolUse hook
payloads, but observe.sh only checked for `tool_output` and `output`.
This caused all observations to have empty output fields, making the
observer pipeline blind to tool results.

Adds `tool_response` as the primary field to check, with backward-
compatible fallback to the existing `tool_output` and `output` fields.

ispaydeu · 2026-03-10 19:14:56 -07:00

708c265b4f

fix: resolve PR 371 portability regressions

Affaan Mustafa · 2026-03-09 22:49:43 -07:00

af51fcacb7

fix: harden hook portability and plugin docs

Affaan Mustafa · 2026-03-09 22:49:43 -07:00

440178d697

fix: force UTF-8 for instinct CLI file IO (#353 )

Frank · 2026-03-07 14:47:35 -08:00

e9577e34f1

fix(hooks): scrub secrets and harden hook security (#348 )

* fix(hooks): scrub secrets and harden hook security

- Scrub common secret patterns (api_key, token, password, etc.) from
  observation logs before persisting to JSONL (observe.sh)
- Auto-purge observation files older than 30 days (observe.sh)
- Strip embedded credentials from git remote URLs before saving to
  projects.json (detect-project.sh)
- Add command prefix allowlist to runCommand — only git, node, npx,
  which, where are permitted (utils.js)
- Sanitize CLAUDE_SESSION_ID in temp file paths to prevent path
  traversal (suggest-compact.js)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(hooks): address review feedback from CodeRabbit and Cubic

- Reject shell command-chaining operators (;|&`) in runCommand, strip
  quoted sections before checking to avoid false positives (utils.js)
- Remove command string from blocked error message to avoid leaking
  secrets (utils.js)
- Fix Python regex quoting: switch outer shell string from double to
  single quotes so regex compiles correctly (observe.sh)
- Add optional auth scheme match (Bearer, Basic) to secret scrubber
  regex (observe.sh)
- Scope auto-purge to current project dir and match only archived
  files (observations-*.jsonl), not live queue (observe.sh)
- Add second fallback after session ID sanitization to prevent empty
  string (suggest-compact.js)
- Preserve backward compatibility when credential stripping changes
  project hash — detect and migrate legacy directories
  (detect-project.sh)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(hooks): block $() substitution, fix Bearer redaction, add security tests

- Add $ and \n to blocked shell metacharacters in runCommand to prevent
  command substitution via $(cmd) and newline injection (utils.js)
- Make auth scheme group capturing so Bearer/Basic is preserved in
  redacted output instead of being silently dropped (observe.sh)
- Add 10 unit tests covering runCommand allowlist blocking (rm, curl,
  bash prefixes) and metacharacter rejection (;|&`$ chaining), plus
  error message leak prevention (utils.test.js)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(hooks): scrub parse-error fallback, strengthen security tests

Address remaining reviewer feedback from CodeRabbit and Cubic:

- Scrub secrets in observe.sh parse-error fallback path (was writing
  raw unsanitized input to observations file)
- Remove redundant re.IGNORECASE flag ((?i) inline flag already set)
- Add inline comment documenting quote-stripping limitation trade-off
- Fix misleading test name for error-output test
- Add 5 new security tests: single-quote passthrough, mixed
  quoted+unquoted metacharacters, prefix boundary (no trailing space),
  npx acceptance, and newline injection
- Improve existing quoted-metacharacter test to actually exercise
  quote-stripping logic

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

* fix(security): block $() and backtick inside quotes in runCommand

Shell evaluates $() and backticks inside double quotes, so checking
only the unquoted portion was insufficient. Now $ and ` are rejected
anywhere in the command string, while ; | & remain quote-aware.

Addresses CodeRabbit and Cubic review feedback on PR #348.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

jtzingsheim1 · 2026-03-07 14:47:31 -08:00

9661a6f042

feat: deliver v1.8.0 harness reliability and parity updates

Affaan Mustafa · 2026-03-04 14:48:06 -08:00

48b883d741

fix(continuous-learning-v2): observer background process crashes immediately (#312 )

* fix(continuous-learning-v2): observer background process crashes immediately

Three bugs prevent the observer from running:

1. Nested session detection: When launched from a Claude Code session,
   the child process inherits CLAUDECODE env var, causing `claude` CLI
   to refuse with "cannot be launched inside another session". Fix: unset
   CLAUDECODE in the background process.

2. set -e kills the loop: The parent script's `set -e` is inherited by
   the subshell. When `claude` exits non-zero (e.g. max turns reached),
   the entire observer loop dies. Fix: `set +e` in the background process.

3. Subshell dies when parent exits: `( ... ) & disown` loses IO handles
   when the parent shell exits, killing the background process. Fix: use
   `nohup /bin/bash -c '...'` for full detachment, and `sleep & wait`
   to allow SIGUSR1 to interrupt sleep without killing the process.

Additionally, the prompt for Haiku now includes the exact instinct file
format inline (YAML frontmatter with id/trigger/confidence/domain/source
fields), since the previous prompt referenced "the observer agent spec"
which Haiku could not actually read, resulting in instinct files that
the CLI parser could not parse.

* fix: address review feedback on observer process management

- Use `env` to pass variables to child process instead of quote-splicing,
  avoiding shell injection risk from special chars in paths
- Add USR1_FIRED flag to prevent double analysis when SIGUSR1 interrupts
  the sleep/wait cycle
- Track SLEEP_PID and kill it in both TERM trap and USR1 handler to
  prevent orphaned sleep processes from accumulating
- Consolidate cleanup logic into a dedicated cleanup() function

* fix: guard PID file cleanup against race condition on restart

Only remove PID file in cleanup trap if it still belongs to the
current process, preventing a restarted observer from losing its
PID file when the old process exits.

zzzhizhi · 2026-03-02 22:23:01 -08:00

adc0f67008

fix: resolve CI failures on main — lint, hooks validator, and test alignment

- Fix MD012 trailing blank lines in commands/projects.md and commands/promote.md
- Fix MD050 strong-style in continuous-learning-v2 (escape __tests__ as inline code)
- Extract doc-file-warning hook to standalone script to fix hooks validator regex parsing
- Update session-end test to match #317 behavior (always update summary content)
- Allow shell script hooks in integration test format validation

All 992 tests passing.

Affaan Mustafa · 2026-03-02 22:15:46 -08:00

1df0a53f22

feat: project-scoped instinct isolation

* feat: add project-scoped instinct isolation

* fix(continuous-learning-v2): harden instinct loading and promotion safety; sync v2.1 command docs

* fix(ci): make copilot-setup-steps a valid GitHub Actions workflow

* fix(hooks): stabilize docs warning inline JS regex parsing

Harry Kwok · 2026-03-01 12:07:13 -08:00

5818e8adc7

Add frontend slides skill across platforms

Affaan Mustafa · 2026-02-27 05:39:31 -08:00

87fc2d5089

feat: add security guides and sanitize external links across repo

New articles:
- the-security-guide.md: "The Shorthand Guide to Securing Your Agent" (595 lines)
  Attack vectors, sandboxing, sanitization, OWASP Top 10, observability
- the-openclaw-guide.md: "The Hidden Danger of OpenClaw" (470 lines)
  Security analysis of OpenClaw, MiniClaw thesis, industry evidence

External link sanitization (22 files across EN, zh-CN, zh-TW, ja-JP, .cursor):
- Removed third-party GitHub links from skills and guides
- Replaced with inline descriptions to prevent transitive prompt injection
- Kept official org links (Anthropic, Google, Supabase, Mixedbread)

Affaan Mustafa · 2026-02-25 07:20:42 -08:00

a9b104fc23

Merge pull request #273 from bintocher/bintocher/issue-246

LGTM — Origin metadata for distributed skills. Pure metadata addition.

Affaan Mustafa · 2026-02-24 09:24:28 -08:00

4dbc0aa966

fix: add origin metadata to skills for traceability

Add origin field to all skill files to track their source repository.
This enables users to identify where distributed skills originated from.
Fixes affaan-m/everything-claude-code#246

Stanislav Chernov · 2026-02-23 19:00:57 +03:00

48dafdd288

address review: remove .cursor/ duplicate, use is not None checks

Changes based on CodeRabbit review feedback:

1. Remove entire .cursor/ directory — it was an identical copy of the
   main skills/commands/agents/rules, causing maintenance drift.
   Users of Cursor can reference the canonical files directly.

2. Use explicit `is not None` checks instead of truthiness for
   parsed['input'] and parsed['output']. Empty strings or empty
   dicts are valid values that should be preserved.

tsli · 2026-02-21 08:46:13 +08:00

dbe737cc0b

fix: use CLI argument for hook phase detection in observe.sh

The observe.sh script receives "pre" or "post" as $1 from the hook
config, but the Python code was looking for a "hook_type" field in
the stdin JSON. Claude Code does NOT include "hook_type" in the
JSON payload passed to hooks, so it always defaulted to "unknown",
causing all observations to be recorded as "tool_complete" —
PreToolUse events were never distinguished from PostToolUse.

Fix: capture $1 as HOOK_PHASE and pass it to Python via env var.
This also fixes TIMESTAMP export in the .cursor copy where inline
`VAR=val cmd` syntax didn't propagate to the python subprocess.

tsli · 2026-02-21 08:45:54 +08:00

cb4e4ca711

fix: correct TIMESTAMP environment variable syntax in observe.sh

The inline environment variable syntax `TIMESTAMP="$timestamp" echo ...` 
does not work correctly because:
1. The pipe creates a subshell that doesn't inherit the variable
2. The environment variable is set for echo, not for the piped python

Fixed by using `export` and separating the commands:
- export TIMESTAMP="$timestamp"
- echo "$INPUT_JSON" | python3 -c "..."

This ensures the TIMESTAMP variable is available to the python subprocess.

Fixes #227

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

黄飞虹 · 2026-02-14 21:25:50 +08:00

1f74889dbf

fix: include .md files in instinct-cli glob (completes #216 )

The observer agent creates instinct files as .md with YAML frontmatter,
but load_all_instincts() only globbed *.yaml and *.yml. Add *.md to the
glob so instinct-cli status discovers all instinct files.

Affaan Mustafa · 2026-02-13 01:26:37 -08:00

e9343c844b

58 Commits