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/trotsky1997/citeclaw/agents-mdgit clone --depth 1 https://github.com/trotsky1997/citeclawWhat 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 | $0.00632 | $0.00632 |
| Opus 5 | $0.00316 | $0.00316 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
citeclaw 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 yesterday.
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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Citoid is a Node.js service with a flat top-level layout.
server.js: service entrypoint (service-runner, launched via Bun script).app.js: Express app initialization, middleware, route loading, and config defaults.routes/: API route handlers (citoid,info,root).lib/: core business logic (citation pipeline, Zotero integration, translators, external API adapters).test/: Mocha test suites by area:features/app,features/errors,features/scraping,features/unit,zotero.config.dev.yaml,config.prod.yaml,config.yaml: runtime configuration..pipeline/anddist/: CI/container build configuration and packaging artifacts.
Build, Test, and Development Commands
Use npm with Node.js 20 or 22.
npm install: install dependencies.npm run start: run viaservice-runnerusingconfig.yaml.npx citeclaw <args>: run CLI from npm.npm run test: lint + core feature suites.npm run test:zotero: full test run including Zotero-heavy tests.npm run coverage: runnyccoverage.npm run lint/npm run lint:fix: enforce/fix ESLint rules.
Coding Style & Naming Conventions
- Follow ESLint config
wikimedia/server(.eslintrc.json). - Use tabs for indentation and single quotes in JS, matching existing files.
- Prefer
camelCasefor variables/functions; keep existing class-style filenames inlib/(for exampleCitoidService.js). - Route and translator files are typically lowercase (
routes/info.js,lib/translators/crossRef.js).
Testing Guidelines
- Frameworks: Mocha + Chai;
nockfor HTTP mocking;nycfor coverage. - Place tests near matching domains (
test/features/unit/*,test/features/scraping/*, etc.). - Name tests by behavior or integration target (for example
semantic-scholar-service.js,redirect.js). - Run
npm run testbefore submitting; runnpm run test:zoterowhen changing Zotero/translators/scraping flow.
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.
- yesterday First seen · 45 lines · 632 tokens per session scan A 1125442176cf
citeclaw AGENTS.md is an instructions file published in the GitHub repository trotsky1997/citeclaw (5 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 632 tokens to every session, about $0.0032 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
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.