Borrowing it
Nothing to install: this file belongs to XBP-Europe/sagemath-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/XBP-Europe/sagemath-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/XBP-Europe/sagemath-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/xbp-europe/sagemath-mcp/agents-md)<a href="https://agentmods.dev/instructions/xbp-europe/sagemath-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/xbp-europe/sagemath-mcp/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/xbp-europe/sagemath-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/xbp-europe/sagemath-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.01817 | $0.01817 |
| Opus 5.5 | $0.00727 | $0.00727 |
| Sonnet 5.5 | $0.00363 | $0.00363 |
| Haiku 4.5 | $0.00182 | $0.00182 |
Grade A, and why
sagemath-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 today.
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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Playbook
Environment & Setup
uv pip install -e .[dev]primes the venv with runtime+dev extras; inside the Sage container usesage -python -m pip ...(what the image andmake sage-depsdo).make sage-container(script:scripts/setup_sage_container.sh) starts the development Sage container the integration tests run in; it is not a runtime deployment.- Keep
TODO.mdin sync with outstanding initiatives; the unchecked items at the bottom reflect the current priority queue. docker-compose.ymlspins up the Sage-backed MCP server locally; the Helm chart undercharts/sagemath-mcpmirrors the deployment knobs for Kubernetes and enforces the non-rootsageuser (UID/GID 1001 on SageMath 10.10).- Release workflow publishes signed images to
ghcr.io/xbp-europe/sagemath-mcp; verify with Cosign if you consume the container directly. - Configure Git hooks after cloning:
git config core.hooksPath .githooks(pre-push runsuv run ruff check). - Use
scripts/run_ci_simulation.shto approximate.github/workflows/ci.ymllocally (requires Docker, Helm, uv; it uses whichever Docker Compose is installed and says so, rather than skipping the smoke test when only v2 is present). - Every workflow installs the uv pinned in
.tool-versions, and a test fails on asetup-uvstep that does not read it. Dependabot cannot move the pin: change it by hand, re-runmake passagemath-lockwith the new uv, and commit both together. - The checks branch protection requires on
mainare listed inTESTING.md(CI). Renaming or adding a required job means changing branch protection too, and the count stated inTESTING.md,SUPPORT.mdandCLAUDE.md.
Fast Commands
make lint→uv run ruff check(Bandit rulesSapply tosrc/)make typecheck→uv run mypyoversrc/sagemath_mcp; CI's lint job runs itmake test→ pure-Python pytest suite (uv run pytest)make integration-test→ runs pytest inside the Sage container and captures logs (integration.log,integration-artifacts.tar.gz)make build→uv run python scripts/build_release.py(sdist/wheel; respects prerequisite guardrails)make all→ convenience alias (make test+make integration-test); keep targets separate when adding CI steps.make allowlist→ regeneratessrc/sagemath_mcp/allowlist.pyfrom the installed Sage. Two steps on purpose: the generator imports the module it writes, so a single redirect truncates its own input. Review every added name before committing.make cli-extended→ drives the real Claude/Gemini/Codex CLIs and asserts from the proxy wire log that a tool was called. Costs model credits.cli-nightly.ymlis scheduled but has no API-key secrets, so it skips every CLI; run this by hand before a release.
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.
- today Changed · +4 lines · +293 tokens per session 69b7254a1148
- 14d ago Changed · +1 lines · +88 tokens per session 67ffb6222e22
- 17d ago Changed · +1 lines · +42 tokens per session b1fdabe892c7
- 22d ago Changed 300ede44efab
- 1mo ago Changed · +22 tokens per session 872f97c24520
- 1mo ago Changed · +3 tokens per session 1b96644fe7ec
- 1mo ago First seen · 67 lines · 1,369 tokens per session scan A 1a2ec64a2232
sagemath-mcp AGENTS.md is an instructions file published in the GitHub repository XBP-Europe/sagemath-mcp (18 stars, last pushed today), licensed MIT. It adds 1,817 tokens to every session, about $0.0073 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.