Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add V-Songbird/slag/plugin install jigWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/v-songbird/slag/inventory)<a href="https://agentmods.dev/skills/v-songbird/slag/inventory"><img src="https://agentmods.dev/badge/skills/v-songbird/slag/inventory.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00203 | $0.02711 |
| Opus 5 | $0.00102 | $0.01355 |
| Sonnet 5 | $0.00041 | $0.00542 |
| Haiku 4.5 | $0.00020 | $0.00271 |
Grade A, and why
inventory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
jig:inventory
Three surfaces, one job each. /jig:jig installs. /jig:review reports what the
guards have caught and acts on it. This one reports what is here — and
stops. Nothing in this skill arms, disarms, retires, waves off or installs
anything, and offering to would be taking another skill's job.
Everything comes from one command:
node "${CLAUDE_PLUGIN_ROOT}/scripts/jig.js" inventory
Run it from the project root. If node is not on PATH (fnm/nvm setups),
register it the way the project's CLAUDE.md says to, then rerun. If the command
refuses because the install predates the rework, send the user to /jig:jig,
which runs the migration, and stop — nothing below reads correctly until then.
An argument narrows the report to one section: guards, checks, files or
lanes. With no argument, print all four in that order.
Every guard, check and file gets the same two-part treatment: a sentence saying what it does in plain words, then the facts under it. Readable first, checkable second. Never one without the other — a sentence nobody can verify is a claim, and a field dump nobody can read is not a report.
1. Guards — what runs inside a session
guardsProblem non-null comes first, before anything else in the report. It
means jig refused the guard config outright, so guards is empty for that
reason and not because nothing is installed. Print it verbatim and send the user
to /jig:jig.
installed: false is the other reason guards can be empty, and it is not the
same one: there is no .jig/config.json here at all — jig was never installed,
or revert took it back out. why is the sentence for it. Say that instead of
showing an empty list, which reads as "everything was retired".
guards[], one row per configured guard. watches is the new half and the
reason this skill exists:
watches.event—PreToolUse(before the call, which is where abash-guardand anedit-guardboth run) orPostToolUse(after the edit, where the olderedit-observe-guardruns and the bytes have already landed).watches.toolsnames the tools it sees, and it is the lever that decides them: the two events no longer split Bash from Edit.watches.paths— the globs it looks at.watches.patterns— how many matchers it carries. The matchers themselves are counted, never printed: they live behind an approval boundary and a report is not a place to re-issue one.watches.deny— the reply an armed match shows. Null means this guard cannot arm at all, whatever its row says. Say that out loud.mode—armed(it blocks) orobserve(it records and lets the call through), andwhysays what put it there. Printwhyverbatim; paraphrasing an honest limit blurs it.problem— non-null means the guard is broken, not quiet. Report it first and separately. A broken guard read as "never fired" is coverage the user thinks they have.provable: false— a fixture is missing, so this check can never be re-proven and no row naming it can arm.teach— whether an observing match also says so in the transcript: one line of context carrying this guard's id and its deny triple, and no source. Off unless the guard's own row set it, and available on either runner. Report it where it is on; a guard that teaches is one the owner will hear from and should be able to find here.provenance: "assumed"— a default the owner never saw. Label it as one every time it is reported.
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.
- yesterday Changed · +54 lines f74d76fc6213
- 6d ago First seen · 130 lines · 203 tokens per session scan A 12db84ba57e9
inventory is a skill published in the GitHub repository V-Songbird/slag (1 stars, last pushed 2d ago), licensed MIT. It adds 203 tokens to every session and 2,711 once invoked, about $0.0010 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
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…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…