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/generate)<a href="https://agentmods.dev/skills/jatinmayekar/openwiki-for-claude-code/generate"><img src="https://agentmods.dev/badge/skills/jatinmayekar/openwiki-for-claude-code/generate.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 | $0.00051 | $0.00858 |
| Opus 5 | $0.00026 | $0.00429 |
| Sonnet 5 | $0.00010 | $0.00172 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
generate 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 7d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenWiki: generate
Build a first-pass OpenWiki-format wiki for the current repository, doing the work yourself with
your own tools (Read, Grep, Glob, Write, Edit, Bash for git). Do not call the openwiki CLI and
do not require any API key — you are the inference engine, which is what the user already pays
for.
First, read the format spec: ${CLAUDE_PLUGIN_ROOT}/reference/openwiki-format.md. It is the
source of truth for layout, the metadata file, the exact AGENTS.md/CLAUDE.md reference block,
writing principles, section rules, and security rules. Follow it precisely so output is compatible
with the OpenWiki CLI.
Steps
- Check for an existing wiki. If
openwiki/already exists with real content, tell the user and switch to the update behavior (/openwiki:update) instead of overwriting. Never clobber an existing wiki. - Confirm repo + git context. Determine the repo root. Run
git rev-parse HEAD(capture for metadata) and skim recent history (git log --oneline -20) for high-signal context. If it's not a git repo, proceed and use an emptygitHead. - Inventory (targeted discovery). Identify existing docs, entrypoints, package/config files,
major domain folders, routing, data/schema files, tests, and operational scripts. Use
rg --fileswith excludes (.git,node_modules,dist,build, caches,openwiki/) and short targeted reads. Do not read every file. For a large repo with several independent domains, you may dispatch 1–2 read-only Explore subagents to summarize domains in parallel — they must only inspect and report, never write. - Plan. Write a temporary
openwiki/_plan.mdlisting intended pages, the source evidence for each, and open questions. You will delete it in step 7. - Write the wiki. Create
openwiki/quickstart.mdfirst (overview + links to every section), then the smallest set of linked section pages that explains the repo well. Respect the init cap (~8 pages max; tiny repos: quickstart + 1–2 pages). Ground every claim in evidence with inline source references. Capture both technical detail and business/product logic, and change-oriented guidance for future agents. - Wire up agent instruction files. Add the exact OpenWiki reference section (see the format
spec) to top-level
AGENTS.md/CLAUDE.mdper the rules there. - Finalize. Delete
openwiki/_plan.md. Review theopenwiki/tree and merge/remove any thin or single-file-directory pages. - Write metadata. Create
openwiki/.last-update.jsonwithcommand: "init",updatedAtfromdate -u +%Y-%m-%dT%H:%M:%S.000Z(run it — don't guess the time), thegitHeadfrom step 2, andmodelset to your Claude Code model id (or"claude-code"). - Report. Summarize the pages created and the AGENTS.md/CLAUDE.md changes. Do not paste subagent notes; give a clean summary and any important caveats.
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.
- 7d ago First seen · 51 lines · 51 tokens per session scan A b7dd1ae13ae2
generate is a skill published in the GitHub repository jatinmayekar/openwiki-for-claude-code (18 stars, last pushed 2mo ago), licensed MIT. It adds 51 tokens to every session and 858 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…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…