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/backblaze-labs/genblaze/claude-mdgit clone --depth 1 https://github.com/backblaze-labs/genblazeWrote 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/backblaze-labs/genblaze/claude-md)<a href="https://agentmods.dev/instructions/backblaze-labs/genblaze/claude-md"><img src="https://agentmods.dev/badge/instructions/backblaze-labs/genblaze/claude-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 | $0.00415 | $0.00415 |
| Opus 5 | $0.00208 | $0.00208 |
| Sonnet 5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
genblaze CLAUDE.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 6d 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
Genblaze — Claude Code Config
- Follow AGENTS.md at all times
- Read order: README.md → ARCHITECTURE.md → AGENTS.md → relevant feature doc
- Plans go in
docs/exec-plans/active/ - Test commands:
make test(full-suite gate),/test-package <name>(one package),/test-package changed(only changed packages) - Quick single-file run:
cd libs/core && pytest tests/unit/<file>.py -v - Lint:
make lint. Python edits are auto-formatted via.claude/hooks/auto-format.sh. - Always run
make testbefore considering work complete - Update docs in the same PR as code changes
- Keep diffs minimal — only change what's needed
- Adding a new connector: use
/scaffold-provider. Before tagging a release: runmake pre-releaseand read RELEASING.md. After publish:make post-release VERSION=<umbrella-version>. Auditing docs freshness:/verify-docs. - Release flow: tag name follows the CHANGELOG wave header (
v0.3.0), not any single package's version. Workflow at.github/workflows/release.ymltriggers on GitHub Release creation;workflow_dispatchruns a TestPyPI dry-run. - CI policy: Dependabot PRs run NO CI. Every job in
.github/workflows/ci.ymlandsecurity.ymlis guarded byif: ${{ github.actor != 'dependabot[bot]' && github.event.pull_request.user.login != 'dependabot[bot]' }}. When adding a job to anypull_request-triggered workflow, copy that same guard onto it, otherwise Dependabot PRs would start running CI again.release.ymlhas nopull_requesttrigger, so it needs no guard.
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.
- 6d ago First seen · 16 lines · 415 tokens per session scan A 15342dba9ef1
genblaze CLAUDE.md is an instructions file published in the GitHub repository backblaze-labs/genblaze (558 stars, last pushed today), licensed MIT. It adds 415 tokens to every session, about $0.0021 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 2026-08-30.
Other instructions, from other repositories
jesse AGENTS.md
AGENTS.md instructions for jesse-ai/jesse, covering jesse repository guide for ai agents, skills, key characteristics, central framework and technology stack.
laravel AGENTS.md
AGENTS.md instructions for laravel/laravel, covering laravel application, prerequisites and agent setup.
AgentEval copilot-instructions.md
Copilot instructions for AgentEvalHQ/AgentEval, covering agenteval - ai coding agent instructions, architecture overview, environment setup, optional: secondary models for comparison and build & test commands.
zhin zhin-plugin.instructions.md
Instructions for zhinjs/zhin, covering zhin plugin runtime authoring, package contract, convention directories, imports and native typescript and command routes.
LarAgent AGENTS.md
Instructions for MaestroError/LarAgent, covering purpose, key principles, planning, executing plan and testing.
igniter-js GEMINI.md
Gemini CLI instructions for felipebarcelospro/igniter-js, covering 1. identity and profile, 2. about the igniter.js monorepo, 3. personality and communication, 4. lia's core responsibilities (the 4 pillars) and 5. technical guidelines and methodology.