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/tmustier/code-mode-mcp/agents-mdgit clone --depth 1 https://github.com/tmustier/code-mode-mcpWhat 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 | $0.00214 | $0.00214 |
| Opus 5 | $0.00107 | $0.00107 |
| Sonnet 5 | $0.00043 | $0.00043 |
| Haiku 4.5 | $0.00021 | $0.00021 |
Grade A, and why
code-mode-mcp 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.
What it actually says
Agent guide
Commands
- Install:
npm ci - Type-check:
npm run check - Test:
npm test - Full release check:
npm run prepublishOnly
Boundaries
- Keep the public surface compact: Code Mode is one
execMCP tool with in-code discovery. - Do not modify Pi or
codex-computer-use-mcpfrom this repository. - Generated code intentionally has the same host authority as this Node process.
node:vmis used for execution control, not as a security boundary. - The standalone stdio process is the fault-containment boundary. Do not add a child or isolate per execution without evidence that this boundary is insufficient.
- Standard output is reserved for MCP. Diagnostics belong on standard error and must not include secrets or tool payloads.
- Preserve nested MCP cancellation, progress, rich content, sampling, roots, and elicitation decisions. Never fabricate elicitation acceptance or rejection.
- Keep tool outputs in memory. Do not persist intermediate tool results or screenshots.
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 · 19 lines · 214 tokens per session scan A 7a91e529a92a
code-mode-mcp AGENTS.md is an instructions file published in the GitHub repository tmustier/code-mode-mcp (1 stars, last pushed 1mo ago), licensed MIT. It adds 214 tokens to every session, about $0.0011 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.