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/jezdez/conda-cli-mcp/agents-mdgit clone --depth 1 https://github.com/jezdez/conda-cli-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/jezdez/conda-cli-mcp/agents-md)<a href="https://agentmods.dev/instructions/jezdez/conda-cli-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/jezdez/conda-cli-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 | $0.02088 | $0.02088 |
| Opus 5 | $0.01044 | $0.01044 |
| Sonnet 5 | $0.00418 | $0.00418 |
| Haiku 4.5 | $0.00209 | $0.00209 |
Grade A, and why
conda-cli-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 4d 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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — conda-cli-mcp coding guidelines
Project contract
-
The repository and distribution are named
conda-cli-mcp. The standalone console command isccm, and the Python package isconda_cli_mcp.conda-mcpis reserved for the future umbrella package that bringsconda-cli-mcpandconda-meta-mcptogether. -
The distribution registers
conda mcpthrough conda's public subcommand plugin hook. It launches the server in a clean process and targets the conda installation that loaded the plugin by default. -
The server exposes the CLI accepted by the configured conda executable, including subcommands contributed through conda plugin hooks.
-
Every CLI operation must remain reachable through a raw argv tool. Commands with introspectable argparse definitions also receive generated structured tools.
-
Discover the command catalog once at server startup. Keep the MCP tool list stable for that server lifetime. Installing, removing, or updating a plugin reports that a restart is required.
-
Run conda commands out of process. Conda owns parser dispatch, configuration loading, plugin ordering, command hooks, solver hooks, transaction hooks, reporters, authentication, and exception handling.
-
Do not expose every conda plugin hook as an independent MCP tool. Non-command hooks participate through normal conda execution.
-
Optional plugin integrations must run through public interfaces in the target interpreter. Do not duplicate a plugin's cache format, path resolution, or validation in the MCP server.
-
Shell commands may return activation code or environment changes. Never claim to mutate the shell of the MCP host.
Project structure
-
Keep the package flat until a real grouping requires a subpackage.
-
server.pyowns MCP capabilities, tool listing, and dispatch. -
discovery.pyowns argparse traversal and conversion into the public command catalog. -
execution.pyowns argv construction, subprocess lifetime, cancellation, and output capture.
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.
- 4d ago First seen · 273 lines · 2,088 tokens per session scan A d322fc72b402
conda-cli-mcp AGENTS.md is an instructions file published in the GitHub repository jezdez/conda-cli-mcp (0 stars, last pushed today), licensed BSD-3-Clause. It adds 2,088 tokens to every session, about $0.0104 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.
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.
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.
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).