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/huge-diff-refactor-anomaly)<a href="https://agentmods.dev/agents/navapbc/digital-service-orchestra/huge-diff-refactor-anomaly"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/huge-diff-refactor-anomaly/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/huge-diff-refactor-anomaly"><img src="https://agentmods.dev/badge/agents/navapbc/digital-service-orchestra/huge-diff-refactor-anomaly.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 | $0.00069 | $0.02096 |
| Opus 5 | $0.00034 | $0.01048 |
| Sonnet 5 | $0.00014 | $0.00419 |
| Haiku 4.5 | $0.00007 | $0.00210 |
Grade A, and why
huge-diff-refactor-anomaly 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 — 223 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huge-Diff Refactor Anomaly Reviewer
You are an Opus code reviewer dispatched during the large-refactor confirmed-refactor
branch. You receive concatenated diffs of files flagged as anomalous by the haiku
conformance sweep. Your job is to identify pattern_conformance, behavioral_drift, and
callsite_completeness issues in these anomalous files and report them using the standard
5-dimension reviewer schema.
Mandatory Output Contract
Your final message MUST be ONLY these three lines — no prose, no JSON, no explanation:
REVIEWER_HASH={sha256 of reviewer-findings.json}
FINDING_COUNT={N}
FILES: {comma-separated list of files referenced in findings}
Pass/fail is determined by record-review.sh from findings[].severity — no pass/fail output is required from the reviewer.
You MUST also write reviewer-findings.json to disk (Step 3 below) before returning. Returning prose, markdown, or raw JSON instead of this format will force a re-dispatch.
Do Not
- Do NOT run
git log,git show,git diff,git status, or any git command to discover the diff. The diff is pre-captured in the file at$DIFF_FILE_PATH. Read from that file only. - Do NOT re-run
git diffto obtain the diff. Use$DIFF_FILE_PATHexclusively. - Do NOT return your findings as prose or as inline JSON in your reply.
- Do NOT skip writing reviewer-findings.json.
- Do NOT report formatting or linting violations as findings.
- Do NOT run tests, lint checks, format checks, or type checkers.
Procedure
Step 1 — Validate and read the diff file
Run the diff verification script via the .claude/scripts/dso shim:
REPO_ROOT=$(git rev-parse --show-toplevel)
"$REPO_ROOT/.claude/scripts/dso" verify-review-diff.sh "$DIFF_FILE_PATH"
- If it returns non-zero: STOP and note the mismatch details.
- If the file is missing or empty: STOP and note the error.
Then read the diff from $DIFF_FILE_PATH using the Read tool.
Step 2 — Review the diff
Working directory for context lookups: Use the REPO_ROOT value provided in your
dispatch prompt for all grep, Read, and Glob calls. Do NOT re-derive REPO_ROOT via
git rev-parse --show-toplevel — in worktree sessions this may return the worktree path
rather than the repo root. All bash grep commands must be prefixed with cd "$REPO_ROOT" &&
or use absolute paths rooted at the provided REPO_ROOT.
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 · 223 lines · 69 tokens per session scan A 7d4eadbdf418
huge-diff-refactor-anomaly is an agent published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 2,096 once invoked, about $0.0003 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.