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 commands/localplugins/plugins/docsgit clone --depth 1 https://github.com/localplugins/pluginsWhat 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 | $0.00026 | $0.00585 |
| Opus 5 | $0.00013 | $0.00293 |
| Sonnet 5 | $0.00005 | $0.00117 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
docs 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/docs
Explicit pull of version-matched documentation for $ARGUMENTS. The first
token is the <library> name; anything after it is an optional [topic]
that narrows the fetch (e.g. a specific method, option, or concept).
Run the same resolve → fetch → ground loop the docpin skill uses — see
skills/docpin/SKILL.md for the overview and skills/docpin/references/resolver.md
for the full algorithm. Do not restate the loop here; follow it:
- Detect ecosystem — find the lockfile/manifest nearest the current
project (or workspace, in a monorepo) that references
<library>. Consult the precedence table inreferences/resolver.md§1. If the library isn't found in any lockfile/manifest, it isn't installed in this project — skip to the "not installed" case below. - Resolve the installed version — prefer the locked version from a
lockfile; fall back to resolving a manifest range via the registry
(label as inferred, per
references/resolver.md§2). - Registry lookup + fetch version-pinned docs — per the ecosystem's
recipe (
references/ecosystem-npm.md,ecosystem-pypi.md,ecosystem-crates.md, orecosystem-go.md), fetch the doc source for that exact version. If[topic]was given, narrow the fetch/extraction to that topic; otherwise fetch the general docs entry point. - Distill + ground — apply
references/output-contract.md: extract only what's relevant to[topic](or a general overview if no topic was given), never fabricate a symbol absent from the resolved version's docs, and end the answer with aSource:line naming the resolved<pkg>@<version>and the exact URL(s) fetched.
If the library isn't installed in this project
Resolve the latest published version from the registry instead, and
label the version basis explicitly as latest (unpinned) (the canonical
label from references/output-contract.md §4) — do not present it as if it
were a version-pinned match for this project.
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 First seen · 47 lines · 26 tokens per session scan A 0884db11d2c9
docs is a command published in the GitHub repository localplugins/plugins (5 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 585 once invoked, about $0.0001 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 commands, from other repositories
security-audit-static
Static security audit of AI-built code — map trust boundaries, cross-reference documented intent, self-refute every finding, and report only evidence-backed risks.
performance-audit-static
Static performance audit of AI-built code — find N+1 queries and request waterfalls, over-fetching, missing indexes, and caching opportunities, ranked by effort and impact.
sprint
Sprint lifecycle — plan a sprint, run a retrospective, or generate release notes.
analyze-test
Analyze A/B test results — statistical significance, sample size validation, and ship/extend/stop recommendations.
plan-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results.
write-stories
Break a feature into backlog items — user stories, job stories, or WWA format with acceptance criteria.