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/seifbenayed/cloclo/agents-mdgit clone --depth 1 https://github.com/SeifBenayed/clocloWhat 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 | $0.01050 | $0.01050 |
| Opus 5 | $0.00525 | $0.00525 |
| Sonnet 5 | $0.00210 | $0.00210 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
cloclo 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 2d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cloclo — Project Conventions
Project
cloclo is an open-source Claude Code alternative: a multi-provider AI coding agent CLI. The shipped runtime is claude-native.mjs, a bundled single-file Node.js CLI with zero native dependencies. The editable source lives in src/. Supporting parity/reference implementations exist in claude-native.py, claude-native.go, and rust-sdk/.
Architecture
- CRITICAL:
claude-native.mjsis a build output. Do not edit it directly for normal feature or bug work. Make source changes insrc/, then rebuildclaude-native.mjswithnode build.mjs. - Main source modules live in
src/(utils.mjs,config.mjs,providers.mjs,auth.mjs,security-rules.mjs,security.mjs,browser.mjs,tools.mjs,lsp.mjs,auto-memory.mjs,audit.mjs,teams.mjs,sandbox.mjs,context-refs.mjs,smart-routing.mjs,cron.mjs,engine.mjs,session.mjs,index.mjs). Start there before touching bundled output. - Keep core agent logic provider-agnostic. Provider differences belong in the
PROVIDERScontract and client conversion layers, not inAgentLoop. - Built-in tools are registered through
ToolRegistry; some tools are eager, others deferred and surfaced viaToolSearch. - Extensibility features are built into the main CLI:
CLAUDE.mdloading,.claude/settings*.json, rules, skills, hooks, memory, sessions, and MCP integration. ink-ui.mjscontains the Ink terminal UI; avoid coupling UI-only behavior into non-interactive/NDJSON paths.claude-tool-loop.jsis the NDJSON bridge/runtime wrapper; keep bridge-specific behavior there rather than in provider code.gstack/is a separate subtree with its own docs/conventions; do not assume its patterns apply to the root CLI unless files explicitly integrate.
Key Patterns
- Preserve the single-file distribution model for the main CLI unless a change explicitly requires otherwise.
- When adding a provider, implement the full provider contract: detection, auth/base URL resolution, model transform, client creation, and capabilities.
- Respect instruction-placement differences by provider (
system-blocks,system-message,developer-message,instructions-field). - Keep deferred tools marked as deferred; register
ToolSearchwhen deferred tools exist. - Maintain backward-compatible CLI behavior and help text for user-facing flags where possible.
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.
- 2d ago First seen · 53 lines · 1,050 tokens per session scan A a57f054e1812
cloclo AGENTS.md is an instructions file published in the GitHub repository SeifBenayed/cloclo (114 stars, last pushed 4mo ago), licensed MIT. It adds 1,050 tokens to every session, about $0.0052 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 2026-08-30.
Other instructions, from other repositories
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.
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).
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.