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/shrimbly/project-wiki/wiki-setupnpx skills add shrimbly/project-wiki --skill wiki-setupgit 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-setup)<a href="https://agentmods.dev/skills/shrimbly/project-wiki/wiki-setup"><img src="https://agentmods.dev/badge/skills/shrimbly/project-wiki/wiki-setup.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 | $0.00093 | $0.01236 |
| Opus 5 | $0.00046 | $0.00618 |
| Sonnet 5 | $0.00019 | $0.00247 |
| Haiku 4.5 | $0.00009 | $0.00124 |
Grade A, and why
wiki-setup 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 5d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
wiki-setup
Bootstrap a brand-new project-wiki. This is interactive — you are gathering the
project's identity and starting material, then writing it into the repo. Read
CLAUDE.md first so you know the conventions you're filling in.
1. Check state
- If
CLAUDE.mdno longer contains{{placeholders, the project is already set up. Confirm with the user before re-running (it will overwrite the Project block, the seed wiki pages, and viewer branding). ls annotations/*.json 2>/dev/nulland read any non-empty ones — unlikely on a fresh repo, but check.
2. Gather the essentials — one question at a time (interactive)
Ask for the items below one at a time: a single question, wait for the answer,
then the next. Do not present them as one numbered block — this is a short
onboarding conversation, not a form. Use a separate prompt per question (one
AskUserQuestion call per choice-based question; a plain conversational message for
the free-text description). Offer a sensible default with each so the user can just
accept it, and infer whatever you can rather than asking.
Ask in this order:
- Description — one paragraph: what is this project exploring or building? Ask
this on its own and wait for the reply — it's free-text and becomes the heart of
wiki/overview.md, so get it in the user's words. - Deliverable(s) — what should the wiki ultimately produce (a design doc, an
ADR/decision record, a Notion handoff, a spec…)?
AskUserQuestion, a few concrete options + a default. - Audience — who reads the output (eng, design, product, leadership, mixed)?
AskUserQuestion, options + a default. - Starting material — anything to ingest right now (links, Figma, Notion pages,
meeting transcripts, pasted notes), or none yet?
AskUserQuestion("Yes — I'll share it now" / "None yet"); if yes, collect it (ingested in step 5).
Project name is already known when this runs via new-project-wiki; running
standalone, ask for it first, on its own. Owner defaults to the git identity —
state that default in passing and only ask if they want to change it; don't make it
its own question.
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.
- 5d ago First seen · 98 lines · 93 tokens per session scan A be3d60b34328
wiki-setup is a skill published in the GitHub repository shrimbly/project-wiki (5 stars, last pushed 1mo ago), licensed MIT. It adds 93 tokens to every session and 1,236 once invoked, about $0.0005 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…
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…
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…