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/agents-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/agents-md)<a href="https://agentmods.dev/instructions/backblaze-labs/genblaze/agents-md"><img src="https://agentmods.dev/badge/instructions/backblaze-labs/genblaze/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 | $0.00867 | $0.00867 |
| Opus 5 | $0.00434 | $0.00434 |
| Sonnet 5 | $0.00173 | $0.00173 |
| Haiku 4.5 | $0.00087 | $0.00087 |
Grade A, and why
genblaze 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agents
Repo Purpose
Orchestration framework for generative media pipelines with manifest-based provenance tracking. Produces 16 pip-installable packages: genblaze-core, 13 provider adapter packages (genblaze-openai, genblaze-google, genblaze-runway, genblaze-luma, genblaze-decart, genblaze-replicate, genblaze-elevenlabs, genblaze-stability-audio, genblaze-lmnt, genblaze-hume, genblaze-gmicloud, genblaze-nvidia, genblaze-assemblyai), genblaze-s3, and genblaze-cli.
Architecture Boundaries
libs/core/— Core SDK; no external API dependencieslibs/connectors/replicate/— Replicate-specific; depends on corecli/— CLI commands; depends on corelibs/spec/— Language-neutral wire contract: JSON Schemas + generated TypeScript types (ts/genblaze.d.ts). Schemas are authoritative; any Pydantic model change must regenerate types viamake ts-typesand passtest_spec_conformance.py. No Python dependencies.- Providers never store API tokens in manifests
- See ARCHITECTURE.md for full detail
Invariants and Guardrails
- All changes must pass
make testbefore PR - Canonical JSON hashing must remain deterministic — never change key sort order or float normalization
- Manifest
canonical_hashmust always verify against re-serialized content - Provider adapters must implement
submit/poll/fetch_output— no exceptions - All IDs are UUIDs — never sequential integers
EmbedPolicymust be respected in all embedding paths- Pydantic v2 models only — no v1 compatibility layer
- Docs must be updated in the same PR as code changes (see Doc Update Mapping)
- Python 3.11+ required
Doc Map
- README.md — Product overview, install, quickstart
- ARCHITECTURE.md — System layout, data flows, canonical files
- AGENTS.md — This file; agent table of contents
- RELEASING.md — Release wave naming, publish pipeline, dry-run path
- CONTRIBUTING.md — Dev setup, PR process, release notes via CHANGELOG
- docs/features/ — Feature docs (one per core feature)
- docs/features/maintainer-agent.md — Maintainer agent flow, modes, and invariants (human reference)
- docs/app-workflows.md — User journeys
- docs/dev-workflows.md — Engineering workflows
- docs/exec-plans/active/ — Active execution plans
- docs/exec-plans/completed/ — Completed plans
- docs/exec-plans/tech-debt-tracker.md — Known tech debt
- CLAUDE.md — Claude Code agent config
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 · 57 lines · 867 tokens per session scan A 20a5fcf70f21
genblaze AGENTS.md is an instructions file published in the GitHub repository backblaze-labs/genblaze (557 stars, last pushed today), licensed MIT. It adds 867 tokens to every session, about $0.0043 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.
LarAgent AGENTS.md
Instructions for MaestroError/LarAgent, covering purpose, key principles, planning, executing plan and testing.
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.
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.