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 skills add shrimbly/project-wiki --skill wiki-publishgit clone --depth 1 https://github.com/shrimbly/project-wikiWrote 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/shrimbly/project-wiki/wiki-publish)<a href="https://agentmods.dev/skills/shrimbly/project-wiki/wiki-publish"><img src="https://agentmods.dev/badge/skills/shrimbly/project-wiki/wiki-publish/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/shrimbly/project-wiki/wiki-publish"><img src="https://agentmods.dev/badge/skills/shrimbly/project-wiki/wiki-publish.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00081 | $0.00934 |
| Opus 5 | $0.00041 | $0.00467 |
| Sonnet 5 | $0.00016 | $0.00187 |
| Haiku 4.5 | $0.00008 | $0.00093 |
Grade A, and why
wiki-publish 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 11d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wiki-publish
Produce a curated, audience-ready document (or a small set) in Notion from the wiki's core concepts. The output is a synthesis for readers, not an export of the tree — most readers should never need to open the repo.
1. Decide what "core" means here
Read wiki/index.md and wiki/overview.md. Propose a curated outline — the
handful of concepts/entities/decisions that a reader genuinely needs, in a logical
reading order. Deliberately leave out: stubs, internal scaffolding, granular open
questions, anything status: draft that isn't load-bearing.
Confirm scope with the user via AskUserQuestion:
- Shape — a single "Core Concepts" document, or a small set (e.g. one per major area)? Recommend single unless the material is clearly too big.
- Depth — executive summary, or full narrative with the decisions and
rationale? Match the audience recorded in
CLAUDE.md. - Inclusions — confirm the outline; let them add/drop sections.
2. Get the Notion destination
- Use the Notion MCP to locate a parent (search for a workspace/page), or ask the user to paste a parent page URL/ID.
- Check whether a previously-published version exists (see step 5's record). If so, default to updating it in place rather than creating a duplicate.
- Confirm before writing. Publishing is outward-facing — show the user the target location and the outline, and get an explicit go-ahead before creating or overwriting Notion content.
3. Compose the document(s)
Write for the reader, not as a wiki dump:
- Open with a tight overview (what this is, why it matters).
- One clean section per core concept/entity, in reading order. Explain; don't just transcribe the wiki page. Pull the decisions and their rationale in where they matter.
- Convert internal viewer-URL cross-links (
/wiki-entities-foo/) into either Notion-internal links (if the referenced concept is its own published page) or plain prose references — never leave raw/wiki-...URLs in the output. - Include a diagram if the wiki has one and Notion can render it (embed the mermaid or a rendered image).
- Keep it legible without the repo. Where useful, note "maintained in the project-wiki" so readers know the source of truth.
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.
- 11d ago First seen · 85 lines · 81 tokens per session scan A 9c915b091baf
wiki-publish is a skill published in the GitHub repository shrimbly/project-wiki (5 stars, last pushed 1mo ago), licensed MIT. It adds 81 tokens to every session and 934 once invoked, about $0.0004 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
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
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…