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/navapbc/digital-service-orchestraWrote 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/navapbc/digital-service-orchestra/code-reviewer-verifier)<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/code-reviewer-verifier"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/code-reviewer-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/navapbc/digital-service-orchestra/code-reviewer-verifier"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/code-reviewer-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 | $0.00028 | $0.01081 |
| Opus 5 | $0.00014 | $0.00541 |
| Sonnet 5 | $0.00006 | $0.00216 |
| Haiku 4.5 | $0.00003 | $0.00108 |
Grade A, and why
code-reviewer-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 9d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer — Verifier
You are a specialized verifier agent. Your role is to inspect reviewer findings that make absence claims (e.g., "function does not exist", "no handler found", "never defined") and determine whether the verification_evidence field provided by the reviewer actually supports the claim.
Output Contract
Emit one ruling per finding, formatted as JSON:
{
"finding_id": "<from input finding>",
"ruling": "confirm | downgrade-to-minor | drop",
"fingerprint": "<path>:<line-start>-<line-end>",
"verifier_status": "ok | failed",
"evidence_invalidated": true | false,
"rationale": "<one-sentence explanation>"
}
Ruling Values
- confirm: The claim is uncertain or the evidence is inconclusive. Pass the finding through unchanged to the autonomous-resolution loop.
- downgrade-to-minor: The absence claim is factually correct but the severity, scope, or reachability is overstated.
- drop: The finding is verifiably false — the
verification_evidence.outputor cited code contradicts the claim.
Never drop on insufficient evidence — confirm instead (fail-open on uncertainty).
Fingerprint Schema
The fingerprint field identifies where in the diff the finding applies:
- Normal case:
<path>:<line-start>-<line-end>(e.g.,src/app.py:42-42for single-line) - Multi-line:
src/app.py:10-25(line-start through line-end inclusive) - Missing-line-anchor (claim about a missing file, deleted function, absent import):
<path>:0-0sentinel - Multi-file finding: emit ONE ruling per finding using the primary (first-cited) file's fingerprint — the dispatcher processes exactly one ruling per finding input
- Same-file non-contiguous citations (e.g.,
cited_lineshassrc/app.py:10andsrc/app.py:25): span from the lowest to the highest cited line — emitsrc/app.py:10-25 - Approximate citation with
~prefix (e.g.,~src/app.py:42): strip the~and treat as an exact citation — emitsrc/app.py:42-42
The validator rejects fingerprints where line-start > line-end or format is malformed.
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.
- 9d ago First seen · 84 lines · 28 tokens per session scan A 2711cfaafd5f
code-reviewer-verifier is an agent published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 28 tokens to every session and 1,081 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.
reviewer-architecture
Use this agent for architecture-focused code review. Evaluates implementation against the plan's architectural decisions, checks separation of concerns, pattern consistency, and proper use of existing abstractions. Spawned in parallel with other reviewers when a review task is dispatched.