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/tessaryai/plugins/update-docsnpx skills add tessaryai/plugins --skill update-docsgit clone --depth 1 https://github.com/tessaryai/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 | $0.00061 | $0.00831 |
| Opus 5 | $0.00030 | $0.00415 |
| Sonnet 5 | $0.00012 | $0.00166 |
| Haiku 4.5 | $0.00006 | $0.00083 |
Grade A, and why
update-docs scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
update-docs
Internal crew primitive — dispatched by
/crew:run. You are running because the orchestrator selected this as one step of a larger workflow; carry out the work below. This skill is not meant to be invoked on its own — user requests go to/crew:run.
You are the docs maintainer. You keep documentation accurate and consistent with the code. You operate in one of two modes, inferred from the argument:
- Issue mode — a
docs-labeled issue requests doc changes. - Post-merge mode — a PR was merged; check whether docs need to follow.
The argument is a GitHub issue/PR number (e.g. /crew:update-docs 88) or a ledger slug
(local). In github mode, if ambiguous, check whether it's an open issue or a merged PR with
gh.
0. Load config and mode
python3 "${CLAUDE_PLUGIN_ROOT}/lib/load_config.py"
Use project.docs_index, labels.docs, labels.agent_pr, ledger.dir. Read the docs
index and AGENTS.md/CLAUDE.md to learn how this project organizes and formats docs
(frontmatter, sizing, where each topic lives). Follow the project's existing doc
conventions — match neighbouring files.
Then read ${CLAUDE_PLUGIN_ROOT}/reference/work-model.md and resolve the mode before any
gh call.
1. Gather the change
- GitHub — issue mode:
gh issue view <N> --comments— understand exactly what doc updates are requested. Address all requested items. - GitHub — post-merge mode:
gh pr view <N>andgh pr diff <N>— understand what code changed and what behavior shifted. - Local mode: if there's an implemented change for the task, read its diff
(
git diff <base>...<branch>in the worktree) anddecision.md; otherwise treat the ledgertask.mdas a docs request.
2. Identify affected docs
Map the change to the docs that cover it, using the project's docs index / structure. Read each candidate doc and the relevant source code — verify every claim you write against the actual code. Don't document intended behavior; document real behavior.
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 · 72 lines · 61 tokens per session scan A 91ecdaf311c5
update-docs is a skill published in the GitHub repository tessaryai/plugins (3 stars, last pushed 15d ago), licensed MIT. It adds 61 tokens to every session and 831 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
ghost-decode
Use when a video hides text in moving dots or noise — "ghost font" clips, motion-defined text, random-dot kinematograms, TV-static videos with a secret message, text readable only while playing but invisible in any paused frame, or the user asks what a ghost-font video says.
review
5-pass structured code review — correctness, security, performance, readability, consistency.
scaffold
Project-aware file generation. Reads existing codebase conventions (naming, structure, imports, exports, test patterns) then generates new files that match exactly. Wires generated files into the project's registration points.
design
Generates and maintains a design manifest for visual consistency. In existing projects, reads current styles and documents the design language. In new projects, asks a few questions and generates a starter manifest. The post-edit hook reads the manifest and flags deviations.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
organize
Repository structure only: directory layout, file placement, naming conventions, and where-does-this-belong decisions. Detects the project's convention, audits files against it, and executes move plans with import-path updates. Never changes code inside files beyond the import updates a move forces; in-file…