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 instructions/shrimbly/project-wiki/agents-mdgit 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/instructions/shrimbly/project-wiki/agents-md)<a href="https://agentmods.dev/instructions/shrimbly/project-wiki/agents-md"><img src="https://agentmods.dev/badge/instructions/shrimbly/project-wiki/agents-md.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 | $0.00541 | $0.00541 |
| Opus 5 | $0.00270 | $0.00270 |
| Sonnet 5 | $0.00108 | $0.00108 |
| Haiku 4.5 | $0.00054 | $0.00054 |
Grade A, and why
project-wiki AGENTS.md 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 4d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{{PROJECT_NAME}} — operating manual for agents
The full operating manual is CLAUDE.md. Read it — everything
there applies regardless of which agent you are. This file exists so that
Codex and other agents that look for AGENTS.md find their way in.
The 30-second version
This is a project-wiki: a three-layer, agent-maintained knowledge base.
sources/— faithful captures of external material (one file per source,urlin frontmatter). Mostly immutable. Don't synthesize here.wiki/— the synthesis layer: interlinked entity / concept / decision / open-question pages. This is where understanding accumulates.CLAUDE.md— the schema: conventions and operations.
The viewer/ (Astro) renders both layers with inline annotations; log.md is
the append-only history; annotations/ holds user comments — read them each
session (ls annotations/*.json).
Skills as runbooks
The operations live as skills in .claude/skills/<name>/SKILL.md. If your agent
can invoke Claude Code skills, call them by name (/wiki-ingest). If not, open
the matching SKILL.md and follow it as a step-by-step runbook — they're
written to be readable that way.
wiki-setup— first-time interactive bootstrap.wiki-ingest— capture a new source, then fan out into the wiki.wiki-research— interactive, menu-driven research to deepen the wiki.wiki-publish— publish curated core concepts as Notion document(s).wiki-query— answer a question; file non-trivial answers back.wiki-lint— health-check the wiki.wiki-diagram— keep the mermaid model diagram(s) current.
Non-negotiables
- Pull fresh from source. Re-fetch; don't paraphrase from memory.
- Synthesize in
wiki/, notsources/. - Every wiki claim cites a source.
- Cross-link with viewer URLs (
/wiki-entities-foo/,/notion-bar/), not relative.mdpaths. - Log every operation in
log.md; commit at natural stopping points.
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.
- 4d ago First seen · 46 lines · 541 tokens per session scan A eca43c1d57bf
project-wiki AGENTS.md is an instructions file published in the GitHub repository shrimbly/project-wiki (5 stars, last pushed 1mo ago), licensed MIT. It adds 541 tokens to every session, about $0.0027 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.