Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/surenode-ai/skill-discovery/inventorynpx skills add surenode-ai/skill-discovery --skill inventorygit clone --depth 1 https://github.com/surenode-ai/skill-discoveryWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00089 | $0.00622 |
| Opus 5 | $0.00044 | $0.00311 |
| Sonnet 5 | $0.00018 | $0.00124 |
| Haiku 4.5 | $0.00009 | $0.00062 |
Grade A, and why
inventory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill inventory
skill-discovery walks the known skill folders and standing-instruction files
for every supported coding agent on this machine and reports what is actually
installed. It reads directory structure and SKILL.md metadata — not the
contents of your source files — and by default makes zero network calls.
Running it
Invoke the bundled launcher, which finds the best available runner
(skill-discovery on PATH, else uvx/pipx, else plain Python):
bash "${CLAUDE_PLUGIN_ROOT}/scripts/run-skill-discovery.sh" --dry-run --json
--dry-runguarantees nothing leaves the machine and shows exactly what a report would contain. Keep it on unless the user explicitly wants to upload to a governance server.--jsonreturns a machine-readable report — parse it and summarize for the user. Drop it (or pass--format human) if the user wants the raw tables.- Add
-vto include each item's full path and every location that was checked.
With no path arguments the tool scans where every supported agent stores skills and auto-discovers project-level skills committed inside repos under the home directory. Useful narrowing flags:
--claude/--codex— limit the scan to one agent's locations.--agent <key>— repeatable; restrict to specific agents.--no-discover-projects— global skills only (skip the repo walk).--discover-root <dir>— add a base outside the home directory.--fail-on findings|high— exit non-zero (useful as a CI gate).
Reporting back
After running, summarize for the user:
- Findings first — anything the scanner flagged (unknown, suspicious, or policy-violating skills), with where it lives.
- Skills — name, agent, location, description.
- Instruction files — rules / steering / custom-instruction files that silently change agent behavior every session.
Call out anything the user likely did not install deliberately, and cite the
path so they can inspect it themselves. Do not claim a skill is "safe" — report
what is present and let the user judge. If the launcher reports a missing
Python interpreter, tell the user to install Python 3.9+, uv, or pipx.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 59 lines · 89 tokens per session scan A efeb2a845295
inventory is a skill published in the GitHub repository surenode-ai/skill-discovery (14 stars, last pushed 20d ago), licensed Apache-2.0. It adds 89 tokens to every session and 622 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.