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 jatinmayekar/openwiki-for-claude-code/plugin install openwikiWrote 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/jatinmayekar/openwiki-for-claude-code/update)<a href="https://agentmods.dev/skills/jatinmayekar/openwiki-for-claude-code/update"><img src="https://agentmods.dev/badge/skills/jatinmayekar/openwiki-for-claude-code/update.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 | $0.00054 | $0.00818 |
| Opus 5 | $0.00027 | $0.00409 |
| Sonnet 5 | $0.00011 | $0.00164 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
update 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 6d 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenWiki: update
Refresh the existing openwiki/ wiki so it reflects recent source changes — doing the work
yourself with your own tools (Read, Grep, Glob, Edit, Bash for git). Do not call the
openwiki CLI and do not require any API key.
First, read the format spec: ${CLAUDE_PLUGIN_ROOT}/reference/openwiki-format.md (layout,
metadata, exact AGENTS.md/CLAUDE.md block, principles, security). Updates must stay compatible with
the OpenWiki CLI.
Steps
- Locate the wiki. If
openwiki/doesn't exist yet, tell the user to run/openwiki:generatefirst and stop. - Read prior metadata. Read
openwiki/.last-update.json. Prefer itsgitHeadas the baseline; fall back toupdatedAtif nogitHead. - Find what changed. Use git:
git diff <gitHead>..HEAD --stat, then targeted diffs on the high-signal changed files. Alsogit status/git difffor uncommitted changes touching docs or important source. If shell/git is unavailable, infer from file timestamps and source inspection. - Build a docs-impact plan (do not write it to disk unless helpful): for each meaningful source change → which wiki page is affected → what edit is needed → why. If a page can't be tied to a relevant change, do not touch it.
- Edit surgically.
- Only edit pages made inaccurate/incomplete/misleading by the changes.
- Prefer replacing a stale sentence over adding paragraphs. Preserve accurate structure/wording.
- No formatting-only edits. Don't reformat tables, normalize blank lines, reorder lists, or polish wording unless you're already changing that content for accuracy.
- Don't refresh Source Map / git-evidence / generic "things to watch" sections unless they are materially wrong now.
- Soft diff budget: if fewer than ~5 source files changed, edit at most 1–2 pages. Avoid
touching
quickstart.mdunless top-level product behavior, setup, or navigation changed. If you think >3 pages need edits, reconsider carefully first.
- Check the reference section. Ensure the top-level
AGENTS.md/CLAUDE.mdOpenWiki section is present and current (see the format spec). Refresh only if missing or semantically stale. - No-op is allowed. If nothing relevant changed and the wiki is already accurate, make no edits
at all — leave every file, including
openwiki/.last-update.json, untouched — and tell the user the wiki is already current. (Upstream only records metadata when content actually changes.) - Write metadata (only if you changed wiki content). Update
openwiki/.last-update.jsonwithcommand: "update",updatedAtfromdate -u +%Y-%m-%dT%H:%M:%S.000Z(run it — don't guess), the currentgit rev-parse HEAD, and yourmodel. - Report which pages changed and why, or that the wiki was already current.
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.
- 6d ago First seen · 50 lines · 54 tokens per session scan A 30f80e6fec20
update is a skill published in the GitHub repository jatinmayekar/openwiki-for-claude-code (18 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 818 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 2026-08-30.
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…