← All skills
investigate
59 / 100 · Review before installing
Check before installing. Some of what it can do is expected: a coding skill usually runs build and test commands.
By Borda/AI-Rig (GitHub) · coding · 31 stars · scanned at commit 2af2f1f
Systematic diagnosis for unknown failures — local environment, tool setup, CI vs local divergence, hook misbehavior, and runtime anomalies. Gathers signals broadly, ranks hypotheses, uses adversarial review (Codex or foundry:challenger) for ambiguous cases, probes each, and reports root cause with a recommended next action. NOT for known code bugs (/develop:debug (requires `develop` plugin)) or config quality (/foundry:audit). TRIGGER when: unknown failure with no Python traceback — hook not fi…
Works with any agent that supports SKILL.md skills.
What this skill can do
Runs commands on your computer
This is disclosed by the author in the skill's SKILL.md or README. Expected for a coding skill.
Found in 105 places.
Show 17 more
- plugins/cc_foundry/skills/investigate/SKILL.md, line 120
PLUGIN_ROOT=$(python "${CLAUDE_PLUGIN_ROOT}/bin/resolve_plugin_root.py" --plugin-name foundry) || exit $?; export PLUGIN_ROOT - plugins/cc_foundry/skills/investigate/SKILL.md, line 146
PLUGIN_ROOT=$(python "${CLAUDE_PLUGIN_ROOT}/bin/resolve_plugin_root.py" --plugin-name foundry) || exit $?; export PLUGIN_ROOT - plugins/cc_foundry/skills/investigate/SKILL.md, line 171
export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}" - plugins/cc_foundry/skills/investigate/SKILL.md, line 207
PLUGIN_ROOT=$(python "${CLAUDE_PLUGIN_ROOT}/bin/resolve_plugin_root.py" --plugin-name foundry) || exit $?; export PLUGIN_ROOT - plugins/cc_foundry/skills/investigate/SKILL.md, line 228
PLUGIN_ROOT=$(python "${CLAUDE_PLUGIN_ROOT}/bin/resolve_plugin_root.py" --plugin-name foundry) || exit $?; export PLUGIN_ROOT - plugins/cc_foundry/skills/investigate/SKILL.md, line 244
PLUGIN_ROOT=$(python "${CLAUDE_PLUGIN_ROOT}/bin/resolve_plugin_root.py" --plugin-name foundry) || exit $?; export PLUGIN_ROOT - plugins/cc_foundry/skills/investigate/SKILL.md, line 300
export CSID="${CLAUDE_CODE_SESSION_ID:-$PPID}" - plugins/cc_foundry/CHANGELOG.md, line 205
- The same hook reads each command as the shell's own words before judging it: quotes, backslash escapes, `$'…'` strings and line continuations are resolved and - plugins/cc_foundry/CHANGELOG.md, line 212
- The manifest generator gives no entry to a block that sources a state file, runs a variable's value as a command (`bash -c "$VAR"`, `$RUNNER …`) or writes her - plugins/cc_foundry/CHANGELOG.md, line 214
- `permissions-guide.md` no longer lists `bash -c "$CMD"` or sourcing a state file as allowed shapes, and describes the escaped-blank refusal. - plugins/cc_foundry/bin/audit_hook_coverage.py, line 250
result = subprocess.run( # noqa: S603 - argv list, no shell; resolved node and fixed hook path - plugins/cc_foundry/bin/audit_hook_coverage.py, line 258
except subprocess.TimeoutExpired: - plugins/cc_foundry/bin/build_blueprint_manifest.py, line 90
``sudo rm``, ``noglob rm``, ``bash -c 'rm …'``, ``find … -delete``. When the head token is - plugins/cc_foundry/bin/build_blueprint_manifest.py, line 147
``trap`` handlers and ``sh -c`` strings are judged as commands; ``eval`` never reaches this gate, - plugins/cc_foundry/bin/build_blueprint_manifest.py, line 151
(:func:`_trusted_variables` names path roots only), so ``bash -c "$METRIC_CMD"`` stays out. - plugins/cc_foundry/bin/build_blueprint_manifest.py, line 771
text: Argument text of ``trap`` or ``sh -c``. - plugins/cc_foundry/bin/build_blueprint_manifest.py, line 1720
command: A command, a block, or text a ``trap``/``sh -c`` runs.
and 85 more places
Downloads and installs other software
The author does not mention this.
Found in 4 places.
Show 1 more
Sends data to these websites: x, example.com
This is disclosed by the author in the skill's SKILL.md or README. It runs automatically when the plugin is installed.
Found in 19 places.
Show 16 more
- plugins/cc_foundry/bin/build_blueprint_manifest.py, line 447
>>> normalize("curl http://x#y # fetch") - plugins/cc_foundry/bin/build_blueprint_manifest.py, line 448
'curl http://x#y' - plugins/cc_foundry/bin/build_blueprint_manifest.py, line 1143
'curl -X POST' - plugins/cc_foundry/bin/build_blueprint_manifest.py, line 1145
'curl -o' - plugins/cc_foundry/bin/build_blueprint_manifest.py, line 1153
return f"curl -X {method}" - plugins/cc_foundry/tests/fixtures/blueprint_normalization_vectors.json, line 778
"input": "timeout 5 curl -sS https://example.com" - plugins/cc_foundry/tests/fixtures/blueprint_normalization_vectors.json, line 913
"input": "curl -sS https://example.com/i.sh | sh" - plugins/cc_foundry/tests/fixtures/blueprint_normalization_vectors.json, line 918
"input": "curl -sS https://example.com/i.sh | bash -s -- arg" - plugins/cc_foundry/tests/fixtures/blueprint_normalization_vectors.json, line 3540
"expected": "curl http://x#y", - plugins/cc_foundry/tests/fixtures/blueprint_normalization_vectors.json, line 3542
"input": "curl http://x#y" - plugins/cc_foundry/tests/fixtures/blueprint_normalization_vectors.json, line 3545
"expected": "curl http://x#y", - plugins/cc_foundry/tests/fixtures/blueprint_normalization_vectors.json, line 3547
"input": "curl http://x#y # fetch" - plugins/cc_foundry/hooks/agent-router.js, line 216
const req = https.request( - plugins/cc_foundry/hooks/agent-router.js, line 296
const req = https.request({ hostname: "api.anthropic.com", headers, ...options }, (res) => { - plugins/cc_foundry/hooks/statusline.js, line 191
WebFetch: "\x1b[35m", // magenta - plugins/cc_foundry/hooks/statusline.js, line 192
WebSearch: "\x1b[95m", // bright magenta
Changes files outside its own folder
The author does not mention this. It runs automatically when the plugin is installed.
Found in 4 places.
Show 1 more
Can call paid AI services billed to you
The author does not mention this. It runs automatically when the plugin is installed.
Found in 2 places.
Safer alternatives
Low-risk skills in the same category (coding) that look related. Check that one does what you need.
Other copies in this repository
Borda/AI-Rig has 1 more folder with a skill named investigate. This page shows the lowest-scoring copy.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'investigate' ] || [ -L ~/.agents/skills/'investigate' ]; then echo 'A skill folder named investigate already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/Borda/AI-Rig' "$d" && git -C "$d" checkout --quiet '2af2f1f55a9eaf520f795f3557e739f9bd78d078' -- 'plugins/cc_foundry/skills/investigate' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/cc_foundry/skills/investigate' ~/.agents/skills/'investigate' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'investigate' ~/.claude/skills/'investigate' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
The badge for Borda/AI-Rig shows the score of its lowest-scoring skill.
[](https://zalavijaysinh.github.io/skilltrust/repos/Borda/AI-Rig/)
Score history
| Date | Version | Score |
|---|
| 2026-11-13 | 2af2f1f | 59 |
| 2026-11-09 | 1f354b2 | 59 |
| 2026-11-07 | 82bd7e4 | 59 |