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/utenadev/mistral-managed-queue/agents-mdgit clone --depth 1 https://github.com/utenadev/mistral-managed-queueWhat 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 | $0.02121 | $0.02121 |
| Opus 5 | $0.01060 | $0.01060 |
| Sonnet 5 | $0.00424 | $0.00424 |
| Haiku 4.5 | $0.00212 | $0.00212 |
Grade B, and why
mistral-managed-queue 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 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.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
| `MMQ_FAKE_RESPONSE` | — | Fixed fake response text (else echo prompt) | How it starts
The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project
mistral-managed-queue — Python MCP server + CLI that queues Mistral API calls with
rate limiting (free-tier ~1 req/30s) via SQLite (WAL mode). Package layout under
mmq/. Console script: mmq (mmq.cli:main).
Architecture
mmq/config.py— all constants + env-var defaults (wait times, model, DB timeouts).mmq/db.py— SQLite layer:init_db, task lifecycle (register_task,claim_task,claim_next_task,get_task,touch_task,update_task_status), rate-limit gate (wait_for_rate_limit),purge_tasks,read_queue_status. Task claiming uses SQLiteUPDATE ... RETURNING(needs SQLite >= 3.35).mmq/core.py— Mistral wrapper (call_mistral_apiwith retries + shared gate),FakeMistralClient(offline e2e), queue execution:execute_mistral_queue_async(req)— self-serve path (MCP): registers its own task and claims only its own (avoids cross-claim deadlock; see testsTestExecuteQueueConcurrent).execute_next_task_async/drain_queue_async/watch_queue_async— themmq workworker, which claims pending tasks by priority (DESC) then FIFO.
mmq/cli.py— subcommands:ask,fetch,work,purge,catalog fetch,mcp,--mcp.mmq/mcp_server.py— FastMCP server; toolsask_mistral,get_queue_status.mmq/README_MCP.md— MCP host setup (opt-in; ja/fr siblings alongside).mmq/catalog/— ORR-compatible catalog fetch/validate/write (fetch.py,validate.py,write.py,types.py).write_catalog_yaml(path, document)(order matters). Feature docs:mmq/catalog/README.md(ja/fr siblings).mmq/__init__.py—__version__+ re-exports. Version is kept in sync withpyproject.toml(currently0.2.2).
Key Concepts
- Rate gate: single shared row in SQLite; every API attempt (first included) waits on it, so all processes/CLI/MCP are uniformly throttled. 429s raise the shared backoff.
- Self-serve vs worker: MCP
ask_mistralprocesses its own request inline.mmq fetchonly enqueues;mmq work(worker mode) drains the queue by priority. - Fake API:
MMQ_FAKE_API=1usesFakeMistralClient(echoes prompt unlessMMQ_FAKE_RESPONSEset).MMQ_FAKE_FAIL=429|errorsimulates failures.
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 · 140 lines · 2,121 tokens per session scan B e8c28ff86c3a
mistral-managed-queue AGENTS.md is an instructions file published in the GitHub repository utenadev/mistral-managed-queue (0 stars, last pushed 6d ago), licensed MIT. It adds 2,121 tokens to every session, about $0.0106 per session on Opus 5. A static security scan graded it B with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.