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/cl-ai-project/cl-mcp/agents-mdgit clone --depth 1 https://github.com/cl-ai-project/cl-mcpWrote 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/cl-ai-project/cl-mcp/agents-md)<a href="https://agentmods.dev/instructions/cl-ai-project/cl-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/cl-ai-project/cl-mcp/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 5.1 | $0.00619 | $0.00619 |
| Opus 5 | $0.00309 | $0.00309 |
| Sonnet 5 | $0.00124 | $0.00124 |
| Haiku 4.5 | $0.00062 | $0.00062 |
Grade B, and why
cl-mcp AGENTS.md scanned grade B 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 6d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
Treat the REPL tool as trusted input only; untrusted callers can execute arbitrary code. Prefer `:tcp` during development and secure the port when exposing beyond localhost. When adjusting logging, ensure secrets are red How it starts
The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
@prompts/repl-driven-development.md @prompts/common-lisp-expert.md
Project Structure & Module Organization
The core system lives under src/, grouped by responsibility (log, repl, protocol, tcp, core, run). Each file is serially loaded via cl-mcp.asd; add new packages here and export symbols explicitly. Tests reside in tests/ with mirrored filenames (*-test.lisp) for Rove. Helper clients and bridges are in scripts/. Keep assets such as sample transcripts or captures under tests/fixtures/ if introduced.
Build, Test, and Development Commands
Use cl-mcp REPL, invoke individual suites with run-tests so tests run inside the agent without shelling out.
Temporary Debug Logging
- When cl-mcp shows unintended behavior or hits errors that are hard to diagnose, record each occurrence to a temp file immediately.
- Use a per-session temp log (for example,
/tmp/cl-mcp-debug-<timestamp>.log) and append entries instead of overwriting. - For every entry, include at least: timestamp, command/tool invocation, relevant inputs, observed error/output, and stack trace or restart information when available.
- Redact secrets before writing logs, and reference the temp log in follow-up debugging notes, issues, or PRs.
Coding Style & Naming Conventions
Follow the Google Common Lisp Style Guide: 2-space indent, ≤100 columns, blank line between top-level forms. Each *.lisp begins with (in-package ...) then module-specific declaim. Use lower-case lisp-case for functions, -p predicates, +constants+, and *specials*. Avoid runtime eval and dynamic symbol interning; prefer restarts over signal. Public functions and classes require docstrings; document conditions and restarts in situ.
Testing Guidelines
Write Rove tests before implementations and place them in the matching file under tests/. Name suites after the unit under test (e.g., (deftest protocol-handshake ...)). Ensure new behaviours extend the cl-mcp/tests ASDF component list and keep coverage over initialize/ping, tool discovery, REPL evaluation, logging, and transport boundary cases. Tests must leave listener threads closed and assert JSON payloads explicitly.
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.
- 6d ago First seen · 29 lines · 619 tokens per session scan B 2f46dcf2c7bb
cl-mcp AGENTS.md is an instructions file published in the GitHub repository cl-ai-project/cl-mcp (84 stars, last pushed yesterday), licensed MIT. It adds 619 tokens to every session, about $0.0031 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). 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).
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.
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
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.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.