claude-skills/scripts
Claude d0b479c2a3
feat(engineering): agent-run-forensics, answer about past runs from the trace
Agents answer questions about their own earlier work from memory, and memory
drops the failed test run, the file a sed one-liner rewrote and the edit made
after the last green run. Claude Code and Codex already record every call,
result and exit code on disk; this plugin reads that record instead.

- trace_finder.py: find the run by repo, window, touched file or command text
- trace_timeline.py: numbered steps, --files with SILENT changes, --why STEP
  with every causal edge labelled recorded or inferred by a named rule
- claim_checker.py: typed claims vs the run; STALE, PARTIAL, CONTRADICTED
- UserPromptSubmit hook names the session transcript for questions about the
  past; fail-open, AGENT_RUN_FORENSICS_HOOK=0 disables it
- secrets redacted in every output, no off switch

Idea from PR #1016, rebuilt without the proposer's npm tool (no-vendor rule).
Bundle engineering-advanced-skills 2.14.10 -> 2.14.11; G12 baseline raised by
the new skill's 272 characters.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01L8KYFLjaj5gnwaZdF3RyDn
2026-10-31 09:13:30 +00:00
..
evals feat(engineering): agent-run-forensics, answer about past runs from the trace 2026-10-31 09:13:30 +00:00
audit_skills.py chore(registry,ci): derive counters, register 11 plugins, add CI guards 2026-06-10 14:33:19 +00:00
bump_plugin_versions.py fix: v2.14.0 audit P0/P1 fixes (plugin updates, Codex, mirrors, script paths, two script bugs) (#1048) 2026-10-22 09:50:05 +02:00
check_command_refs.py docs: replace command namespaces that no plugin provides (#1077) 2026-10-31 07:47:03 +01:00
check_dual_publish.py chore(registry,ci): derive counters, register 11 plugins, add CI guards 2026-06-10 14:33:19 +00:00
check_frontmatter.py fix(agents): drop dead skills: values and ignored context: fork (from #939) 2026-10-21 06:59:27 +00:00
check_listing_budget.py ci: add gate G12, a ratchet on each plugin's skill-listing size 2026-10-30 17:24:10 +00:00
check_model_freshness.py chore(scripts): sync derive_counters docs with 5-source gate, rename EXCLUDED_DIRS to EXCLUDED_NAMES 2026-08-25 06:43:51 +00:00
check_model_freshness_allowlist.txt fix(models): remove retired model IDs and stale pricing, flip G7 blocking 2026-08-03 08:55:36 +08:00
check_paths.py fix: v2.14.0 audit P0/P1 fixes (plugin updates, Codex, mirrors, script paths, two script bugs) (#1048) 2026-10-22 09:50:05 +02:00
check_paths_allowlist.txt fix: v2.14.0 audit P0/P1 fixes (plugin updates, Codex, mirrors, script paths, two script bugs) (#1048) 2026-10-22 09:50:05 +02:00
check_plugin_json.py fix(plugins,sync): align four plugin names with their install names; refresh Vibe/Hermes mirrors 2026-10-21 10:08:11 +00:00
check_plugin_versions.py fix: v2.14.0 audit P0/P1 fixes (plugin updates, Codex, mirrors, script paths, two script bugs) (#1048) 2026-10-22 09:50:05 +02:00
check_skill_names.py docs: replace command namespaces that no plugin provides (#1077) 2026-10-31 07:47:03 +01:00
codex-install.bat fix: v2.14.0 audit P0/P1 fixes (plugin updates, Codex, mirrors, script paths, two script bugs) (#1048) 2026-10-22 09:50:05 +02:00
codex-install.sh fix: v2.14.0 audit P0/P1 fixes (plugin updates, Codex, mirrors, script paths, two script bugs) (#1048) 2026-10-22 09:50:05 +02:00
convert.sh fix(convert): copy assets/ into converted integrations 2026-10-29 06:52:28 +07:00
derive_counters.py fix(gate): catch fabricated delta-style counter claims in CHANGELOG.md/CLAUDE.md 2026-09-04 19:07:59 +02:00
extract_release_notes.py feat(release): auto-tag + GitHub Release from CHANGELOG on push to main 2026-05-19 04:00:06 +00:00
gemini-install.sh release: v2.1.1 — skill optimization, agents, commands, reference splits (#297) 2026-03-09 15:54:25 +01:00
generate-docs.py docs(site): generate agent-launcher pages (18th domain) + nav 2026-08-24 17:26:12 +00:00
install.sh feat(integrations): change Augment from flat rules to skill bundles 2026-04-25 04:48:41 +05:30
listing_budget_baseline.txt feat(engineering): agent-run-forensics, answer about past runs from the trace 2026-10-31 09:13:30 +00:00
openclaw-install.sh Dev (#218) 2026-02-25 10:58:52 +01:00
review-new-skills.sh feat(ci): add automated Tessl skill quality review on PRs 2026-04-07 12:21:30 +02:00
smoke_exceptions.txt fix(book-to-skill): guard EPUB XML, cap zip expansion, refuse symlinked trees 2026-08-05 07:31:04 +00:00
smoke_json_baseline.txt fix: close remaining v2.14.0 audit P2 items 2026-10-26 12:56:55 +00:00
smoke_json_output.py fix: close remaining v2.14.0 audit P2 items 2026-10-26 12:56:55 +00:00
smoke_scripts.py polish: PR #838 second-pass nits (non-blocking) 2026-06-11 15:40:45 +00:00
sync-codebuff-skills.py fix: resolve open GitHub issues #805 #806 #807 #748 #785 2026-06-11 03:34:13 +00:00
sync-codex-skills.py Merge origin/dev (#1038 landed) into claude/project-thread-2noqxb 2026-10-21 07:51:35 +00:00
sync-gemini-skills.py fix: v2.14.0 audit P0/P1 fixes (plugin updates, Codex, mirrors, script paths, two script bugs) (#1048) 2026-10-22 09:50:05 +02:00
sync-hermes-skills.py fix(plugins,sync): align four plugin names with their install names; refresh Vibe/Hermes mirrors 2026-10-21 10:08:11 +00:00
sync-vibe-skills.py fix(plugins,sync): align four plugin names with their install names; refresh Vibe/Hermes mirrors 2026-10-21 10:08:11 +00:00
sync_skill_bundles.py chore(phase-0): add dual-publish + plugin.json validation tools 2026-05-09 05:54:15 +00:00
tessl_review_parse.py ci(tessl): score skills with tessl review run and a TESSL_TOKEN 2026-10-31 08:57:32 +00:00
test_derive_counters.py fix(gate): catch fabricated delta-style counter claims in CHANGELOG.md/CLAUDE.md 2026-09-04 19:07:59 +02:00
vibe-install.sh fix: close remaining v2.14.0 audit P2 items 2026-10-26 12:56:55 +00:00