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/localplugins/plugins/docpinnpx skills add localplugins/plugins --skill docpingit 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 | $0.00050 | $0.00854 |
| Opus 5 | $0.00025 | $0.00427 |
| Sonnet 5 | $0.00010 | $0.00171 |
| Haiku 4.5 | $0.00005 | $0.00085 |
Grade A, and why
docpin 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docpin
Ground library code in documentation for the exact version installed in this project — not training-data memory, and not merely "latest."
When to trigger
- Claude is about to write or explain code that imports/calls a third-party library (npm, PyPI, crates.io, or Go module).
- The user asks how to use a named library or framework ("how do I do X with
<lib>", "why isn't<lib>.foo()working", etc.).
When NOT to trigger
- Standard-library / language-builtin APIs (e.g. Python's
os, Node'sfs, Rust'sstd, Go'snet/http) — these aren't version-pinned third-party packages and don't need registry resolution. - Pure algorithm/logic questions with no library API surface involved.
- The project already has a fresh cache hit for this exact
pkg@version(seereferences/caching.md) — reuse it instead of re-fetching.
The resolve → fetch → ground loop
Five steps, detailed in references/resolver.md:
- Detect ecosystem — find the lockfile/manifest nearest the file in focus (lockfile takes precedence over manifest).
- Resolve installed version — read the concrete pinned version from the lockfile, or infer one from a manifest range via the registry.
- Registry lookup — fetch registry metadata to confirm the version and get the repo/docs URLs.
- Fetch version-pinned docs — fetch the actual docs for that exact version, per the ecosystem's recipe.
- Distill + ground — extract what's relevant, then write or explain code against it, citing the version and URL.
For the full algorithm, the file-precedence table, the registry URLs, and the
fallback chain (no lockfile, 404, private package), read
references/resolver.md.
Honesty invariant
Every grounded answer must:
- Cite the resolved version and the exact URL(s) fetched, so the user can verify.
- Never invent a symbol that isn't present in the resolved version's docs
— if a requested API isn't there, say so plainly (e.g. "
useFooBaris not in[email protected]") instead of guessing or fabricating.
What ships with it
7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 80 lines · 50 tokens per session scan A 66abb37f1ecd
docpin is a skill published in the GitHub repository localplugins/plugins (5 stars, last pushed 1mo ago), licensed MIT. It adds 50 tokens to every session and 854 once invoked, about $0.0003 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
brainstorm-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results. Use when setting quarterly OKRs, aligning team goals with company strategy, drafting objectives, or learning how to write effective OKRs.
pre-mortem
Run a pre-mortem risk analysis on a PRD or launch plan. Categorizes risks as Tigers (real problems), Paper Tigers (overblown concerns), and Elephants (unspoken worries), then classifies as launch-blocking, fast-follow, or track. Use when preparing for launch, stress-testing a product plan, or identifying what could go…
ab-test-analysis
Analyze A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when evaluating experiment results, checking if a test reached significance, interpreting split test data, or deciding whether to ship a variant.
dummy-dataset
Generate realistic dummy datasets for testing with customizable columns, constraints, and output formats (CSV, JSON, SQL, Python script). Use when creating test data, building mock datasets, or generating sample data for development and demos.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.