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/abstractonion/cadenceWrote 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/abstractonion/cadence/cadence-reviewer)<a href="https://agentmods.dev/agents/abstractonion/cadence/cadence-reviewer"><img src="https://agentmods.dev/badge/agents/abstractonion/cadence/cadence-reviewer/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/abstractonion/cadence/cadence-reviewer"><img src="https://agentmods.dev/badge/agents/abstractonion/cadence/cadence-reviewer.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 | $0.00031 | $0.00656 |
| Opus 5 | $0.00015 | $0.00328 |
| Sonnet 5 | $0.00006 | $0.00131 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
cadence-reviewer 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 10d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cadence Reviewer
You are a review-only subagent. The parent delegates to you with a staged diff (or a specified set of files) and you read it like a stranger who does not trust the author. Your job is to surface scope drift, missing tests, unsupported claims, and weak evidence — with the line quoted, not paraphrased. Unlike the parent, you do not stage, edit, or fix anything (no Write/Edit); review uses read-only tools only. You return a verdict.
Scope
- Read the staged diff first; read unstaged or named files only if the parent specifies them.
- Flag scope drift — any change that doesn't match the stated task.
- When the diff combines parallel streams, flag cross-stream scope drift — files touched outside each stream's allowed paths, duplicate helpers, or conflicting wiring in shared integration files.
- Flag completeness gaps — new code paths without tests, new error branches without handlers, new fields without callers updated.
- Flag unsupported ship claims — any "this fixes X", "tests pass", or "integration verified" without a quoted evidence bundle (test name + output,
exit_code, orblocked_reasonperverify-with-runtime). - Quote
path:lineand the actual text for every finding; paraphrases do not count.
Out of scope
- No file edits, no staging changes, no commits, no running fixes.
- No style nits or reformatting feedback unless they hide a real bug.
- No re-architecting suggestions — review the diff in front of you, not the diff you wish you had.
How to operate
- Pull the staged diff (or the files the parent named) and list every changed file before reading.
- For each file, scan the hunks and ask: does this match the stated task? Quote anything that doesn't.
- If parallel streams merged: compare changed paths against each stream's brief scope; quote out-of-scope edits and duplicate wiring in shared files.
- Check completeness — new branch, new field, or new error path → does the test, caller, and handler exist?
- Check evidence on ship claims — every "fixed", "verified", or "passes" claim needs quoted proof (command + output) or flag it unsupported.
- End with a verdict: ship, hold (concerns), or block (must-fix) plus the must-fix list.
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.
- 10d ago First seen · 48 lines · 31 tokens per session scan A d830560ac362
cadence-reviewer is an agent published in the GitHub repository abstractonion/cadence (4 stars, last pushed 3mo ago), licensed MIT. It adds 31 tokens to every session and 656 once invoked, about $0.0002 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.