Borrowing it
Nothing to install: this file belongs to ewhauser/bazel-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/ewhauser/bazel-mcp/main/AGENTS.mdgit clone --depth 1 https://github.com/ewhauser/bazel-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/ewhauser/bazel-mcp/agents-md)<a href="https://agentmods.dev/instructions/ewhauser/bazel-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ewhauser/bazel-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/ewhauser/bazel-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/ewhauser/bazel-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 | $0.00351 | $0.00351 |
| Opus 5.5 | $0.00140 | $0.00140 |
| Sonnet 5.5 | $0.00070 | $0.00070 |
| Haiku 4.5 | $0.00035 | $0.00035 |
Grade A, and why
bazel-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 2mo 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.
What it actually says
Agent instructions
This repository implements a token-efficient, local Bazel MCP invocation service. Preserve these invariants:
- The server exposes exactly
bazel.run,bazel.inspect, andbazel.cancel. - MCP stdout is protocol-only; tracing and diagnostics go to stderr.
- Never invoke Bazel through a shell or concatenate request arguments.
- Preserve raw evidence locally while enforcing model-visible byte budgets.
- Keep the crate dependency direction in specification 002. Only the server
depends on
rmcp; the production store is database-free filesystem storage. - Keep reducers deterministic. Fixture updates require reviewed golden diffs.
- Redact secrets before summaries, durable metadata, and telemetry.
Use make build, make test, make check, make test-bazel-matrix,
make fuzz-smoke, and the explicit token benchmark targets. Do not run the long
Abseil benchmark as an ordinary unit test. Use Conventional Commits; Release
Please owns versions and the changelog.
Always use the Bazel MCP tools instead of invoking Bazel or Bazelisk directly.
When using Bazel MCP reveals a performance issue, bug, or agent-workflow
inefficiency caused by MCP behavior, create or update the repository-root
LEARNINGS.md. Record the concrete MCP symptom, its impact on tool calls or
model-visible tokens when applicable, an actionable follow-up, and the Codex
Thread ID where the observation occurred.
Agent-workflow observations are especially valuable when they expose
inefficient protocol behavior, result reduction, or inspection flows. Do not
add general project, Bazel, CI, release, or unrelated workflow learnings. Do not
record secrets or raw sensitive output.
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.
- 2mo ago First seen · 30 lines · 351 tokens per session scan A 61651901751f
bazel-mcp AGENTS.md is an instructions file published in the GitHub repository ewhauser/bazel-mcp (10 stars, last pushed 6d ago), licensed MIT. It adds 351 tokens to every session, about $0.0014 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 2026-08-31.
bazel-mcp AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bazel-mcp AGENTS.mdewhauser/bazel-mcp | Instructions file | 10 | 6d ago | MIT | A | 351 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| vscode ai-customization.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 1,907 | GitHub Copilot |