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/aropan/clist/agents-mdgit clone --depth 1 https://github.com/aropan/clistWhat 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 | $0.01032 | $0.01032 |
| Opus 5 | $0.00516 | $0.00516 |
| Sonnet 5 | $0.00206 | $0.00206 |
| Haiku 4.5 | $0.00103 | $0.00103 |
Grade C, and why
clist AGENTS.md scanned grade C with 1 finding 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 3d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
approval**: no `git push`, `git reset --hard`, `git clean -fd`, no `rm -rf`, How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Short operating contract for AI coding agents working in the CLIST
repository. It holds only the invariants every agent must see without a click;
everything else lives in docs/ and in the skills.
The per-tool files — CLAUDE.md, GEMINI.md, and
.github/copilot-instructions.md — are symlinks to this file, so Claude,
Gemini, Copilot, Cursor, Codex, and any other agent read the same rules.
What CLIST is: a competitive-programming aggregator — see docs/project-context.md.
Golden rules
- Make small, reviewable changes. No large refactors or architectural changes unless explicitly asked.
- Inspect before editing. Read the relevant files and state a short plan before changing code.
- Match surrounding code — naming, structure, comment density, imports. Prefer existing project patterns over introducing new abstractions or dependencies.
- Do not rename public APIs, model fields, DB columns, env vars, or external contracts without asking.
- Never run destructive or outward-facing commands without explicit
approval: no
git push,git reset --hard,git clean -fd, norm -rf, noDROP/DELETE/TRUNCATE, no deploys, nodocker ... prune. - Commit or push only when the user asks.
- Never print or commit secrets — see docs/git-and-safety.md.
- After editing, run the narrowest relevant check first, then broaden — see
docs/testing.md,
docs/linting-formatting.md, and the
run-and-verifyskill. - Be honest about what was and wasn't verified.
Documentation index
| Doc | Use it for |
|---|---|
| docs/project-context.md | What CLIST is; the dual Django + legacy PHP codebase |
| docs/repository-map.md | Where things live in src/, legacy/, config/; risk per area |
| docs/development-environment.md | Docker Compose, the long-running dev service, manage.py commands |
| docs/testing.md | Django test runner; narrow → broad policy |
| docs/linting-formatting.md | Ruff, Biome, PHP-CS-Fixer, editor integration |
| docs/git-and-safety.md | Git policy, off-limits files, destructive-command ban |
| docs/infrastructure.md | Docker services, supervisord, RQ queues, config/ tree, monitoring |
| docs/parsers.md | 1-paragraph overview + pointer to the add-parser skill |
| docs/migrations.md | 1-paragraph overview + pointer to the safe-migration skill |
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.
- 3d ago First seen · 83 lines · 1,032 tokens per session scan C 494e54d9c5e6
clist AGENTS.md is an instructions file published in the GitHub repository aropan/clist (440 stars, last pushed 17d ago), licensed Apache-2.0. It adds 1,032 tokens to every session, about $0.0052 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
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.