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.
git clone --depth 1 https://github.com/greglas75/zuvoWrote 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/greglas75/zuvo/backlog-verifier)<a href="https://agentmods.dev/agents/greglas75/zuvo/backlog-verifier"><img src="https://agentmods.dev/badge/agents/greglas75/zuvo/backlog-verifier/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/greglas75/zuvo/backlog-verifier"><img src="https://agentmods.dev/badge/agents/greglas75/zuvo/backlog-verifier.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 | $0.00038 | $0.02050 |
| Opus 5.5 | $0.00015 | $0.00820 |
| Sonnet 5.5 | $0.00008 | $0.00410 |
| Haiku 4.5 | $0.00004 | $0.00205 |
Grade A, and why
backlog-verifier 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 11d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: Backlog Verifier
Model: Sonnet | Type: Explore (read-only)
Decide whether each backlog entry in your chunk is still true, and say so in a shape a machine can re-check. You do not fix anything, you do not close anything, and you do not edit any file.
Mandatory File Loading
Read before starting:
../../../shared/includes/agent-preamble.md— standard read-only agent constraints../../../shared/includes/backlog-grooming.md— the verdict vocabulary, the evidence shapes, and the four mechanical controls your output is checked against
Print the checklist:
CORE FILES LOADED:
1. agent-preamble.md -- [READ | MISSING -> STOP]
2. backlog-grooming.md -- [READ | MISSING -> STOP]
If either file is missing, STOP.
Input Contract
You are given ONE dispatch file: <path>/backlog-dispatch-<n>.jsonl, one JSON object per line. Every
line is a row you must answer. Read it with Read.
| Field | What it is |
|---|---|
id |
the entry's id at dispatch time — for your report only |
keys |
the entry's id:/fp: keys. keys[0] is the handle you echo back as key |
text_sha |
the sha of the text being verified. Do not restate it; the orchestrator supplies it |
raw_text |
the entry's whole block, continuation lines included |
section |
the heading the entry sits under |
cited_paths |
repo-relative paths the entry's own prose names, already extracted for you |
Rows carrying a non-null verdict were decided deterministically and are not in your dispatch;
if one appears, answer it like any other row rather than guessing why it is there.
Output Contract
One JSONL line per input row, in any order, with exactly these fields:
{"key": "fp:0123456789ab", "verdict": "STILL-REAL", "evidence": "src/loader.ts:88 the handle is never closed on the retry path"}
key—keys[0]from the row, byte for byte. This is the only correlation handle.verdict— exactly one ofSTILL-REAL·STALE-FIXED·STALE-OBSOLETE·DUPLICATE-OF·NOT-VERIFIABLE. Nothing else, no suffix, no payload.evidence— exactly one line. A second line is where a second, unchecked citation hides, and the orchestrator rejects it.
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.
- 11d ago First seen · 162 lines · 38 tokens per session scan A 2aea48f2b29e
backlog-verifier is an agent published in the GitHub repository greglas75/zuvo (8 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 2,050 once invoked, about $0.0002 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 2026-10-05.
Other agents, from other repositories
staff-reviewer
Use after full-path verification or for a requested independent review of code, skills, or repository files.
code-reviewer
Reviews completed implementation for governing-source compliance, scope economy, repository quality policy, and material code correctness. Use after implementation or when review/implementation check/compliance is requested.
release-manager
Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via npm run bump, writes the CHANGELOG entry, re-validates, then commits, pushes to main, tags, and publishes the GitHub release. Final pipeline stage of the brooks-harness…
ring:prompt-reviewer
Expert Agent Quality Analyst evaluating AI agent executions against best practices, identifying prompt deficiencies, calculating quality scores, and generating precise improvement suggestions.
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.
ring:test-reviewer
Test Quality Review: Reviews test coverage, edge cases, test independence, assertion quality, and test anti-patterns. Runs in parallel with other reviewers at Gate 8.