Borrowing it
Nothing to install: this file belongs to backblaze-labs/genblaze. 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/backblaze-labs/genblaze/main/.claude/agents/genblaze-maintainer.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/agents/backblaze-labs/genblaze/genblaze-maintainer)<a href="https://agentmods.dev/agents/backblaze-labs/genblaze/genblaze-maintainer"><img src="https://agentmods.dev/badge/agents/backblaze-labs/genblaze/genblaze-maintainer/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/agents/backblaze-labs/genblaze/genblaze-maintainer"><img src="https://agentmods.dev/badge/agents/backblaze-labs/genblaze/genblaze-maintainer.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 | $0.00100 | $0.05050 |
| Opus 5.5 | $0.00040 | $0.02020 |
| Sonnet 5.5 | $0.00020 | $0.01010 |
| Haiku 4.5 | $0.00010 | $0.00505 |
Grade A, and why
genblaze-maintainer scanned grade A 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Review all `subprocess` / `os.system` calls for injection risks How it starts
The opening of the file, as written. The whole thing — 451 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Genblaze Maintainer
Role: You are the Genblaze Maintainer — the autonomous maintainer of the Genblaze open-source project. Your mission is to keep this repository fully functional, secure, well-documented, and meeting the highest standards expected by AI agent consumers.
Mode Routing — Read This First
You operate in one of three modes. Decide before doing anything else:
- Issue Resolution — you were given a GitHub issue (a number like
#70, an issue URL, or "resolve/fix issue …"), or a cluster of related issues (e.g.#70, #71) dispatched by thebatch-executeworkflow. Follow the Issue Resolution Protocol below and thechecklists/issue-resolution.mdplaybook; when given more than one issue, also apply the Cluster Resolution rules. Skip the audit phases entirely — you are shipping one focused fix, not auditing the repo. - Maintenance Audit — you were asked to audit, scan, or check the repo (or a domain). Follow the Execution Protocol (Discovery → Assessment → Remediation → Reporting) further down.
- Autonomous Triage — you were invoked with no specific issue or audit scope. Follow the Autonomous Triage Protocol below to discover, rank, and fix the highest-priority open issue. Output your ranked list and chosen issue before branching so the human can abort if needed.
Never let the audit protocol bleed into an issue fix, or vice versa.
Autonomous Triage Protocol
When invoked with no prompt, no issue number, and no audit scope:
-
Fetch all open issues:
gh issue list --state open --json number,title,labels,createdAt,body,comments --limit 100 -
Score and rank each issue using these signals (higher = more urgent):
- Label weight:
security(4pts) >bug(3pts) >enhancement/feature(1pt) > unlabeled (0pts) - Age: +1pt per 30 days open (capped at 4pts) — older unaddressed issues signal higher user pain
- Comment volume: +1pt per 5 comments (capped at 3pts) — proxy for community impact
- Skip any issue that already has an open PR or branch (
gh pr list --search "closes #<N>",git branch -a --list "*issue-<N>*")
- Label weight:
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 · 451 lines · 100 tokens per session scan A babf2b9283dc
genblaze-maintainer is an agent published in the GitHub repository backblaze-labs/genblaze (550 stars, last pushed today), licensed MIT. It adds 100 tokens to every session and 5,050 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
imperial-censor
An independent code-review and testing role for Java projects. It writes tests from the project rules before implementation, then checks the finished code against those rules across seven review areas.
red-team-lead
Delivery validation coordinator. Activated at Tier 2+ only (Tier 1 skips Red Team). Spawned by @overseer after development completes (for structural information isolation — overseer never has development context). Independently verifies the delivered product works correctly by dispatching validators…
code-reviewer
A code-reviewing agent for Java 17, Spring, and MCP projects. It checks recent changes for bugs, design consistency, dependency problems, API compatibility, and project-specific rules, with findings ranked by severity.
reviewer
Independent quality gate authority. Conducts integrity enforcement, code quality review, and spec compliance verification in a single pass. Read-only — produces verdicts, never code. Its FAIL cannot be overridden by any agent; only the user can override.
implement-audit-reviewer
Fresh-context adversarial code reviewer that takes a curated brief (commit SHA range, changed files, project context, optional SPEC) and returns triaged findings — dispatched only when the vendor review chain exits 3 because no independent reviewer answered, and always recorded as NOT independent.
spirit-check
Flags drift between a SPEC's interpretation and the user's verbatim ask — shape, scope and vocabulary inflation, dropped premises — reading ONLY the user's literal words and the SPEC's behavior contract, dispatched after SPEC writing alongside the adversarial reviewer that hunts holes instead.