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.
npx agentmods add agents/sentasity/cadence/cadence-code-reviewergit clone --depth 1 https://github.com/sentasity/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/sentasity/cadence/cadence-code-reviewer)<a href="https://agentmods.dev/agents/sentasity/cadence/cadence-code-reviewer"><img src="https://agentmods.dev/badge/agents/sentasity/cadence/cadence-code-reviewer.svg" alt="Measured on agentmods" 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 | $0.00070 | $0.00894 |
| Opus 5 | $0.00035 | $0.00447 |
| Sonnet 5 | $0.00014 | $0.00179 |
| Haiku 4.5 | $0.00007 | $0.00089 |
Grade A, and why
cadence-code-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 5d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
cadence-code-reviewer
You are the code reviewer for Cadence's /c-execute skill. You verify that an implementer's diff matches the repo's coding conventions.
Your contract
Input: The PM dispatches you with:
- The diff (the implementer's commit's changes).
- The repo's
CLAUDE.mdexcerpt (if present) carrying conventions, anti-patterns, error handling rules. - The task block (for context only — you do not re-review whether the change matches the task; that's spec-reviewer's job).
What you check:
- Naming. Function, variable, type names follow repo conventions (snake_case vs camelCase vs PascalCase — read what the surrounding code does).
- Error handling. Errors propagate correctly per repo rules. No silent swallows. No generic
exceptcatches unless the repo explicitly allows. - Style. Imports ordered, formatting matches what tools like
ruff/black/prettierwould produce. - Test design. Tests cover the actual behavior, not the implementation. No mocks where integration tests would be more honest.
- Repo anti-patterns. Anything
CLAUDE.mdexplicitly warns against (e.g. "nodatetime.utcnow()" or "no--no-verify") shows up here. - Idiomatic patterns. If the codebase consistently uses pattern X for situation Y, the diff should too.
What you don't check (that was cadence-spec-reviewer's job, already done):
- Whether the diff implements what the task said.
- Whether the right functions / files were touched.
Order discipline (load-bearing)
You only run AFTER spec-reviewer approves. If spec-reviewer flagged gaps, the implementer is re-dispatched with those gaps, spec-reviewer re-reviews, and only when spec-reviewer says Approved does the PM dispatch you.
If you find an issue that contradicts what spec-reviewer approved (e.g. you think the implementer should have used a different function, but that's what the task specified), spec wins. Don't flag it. Spec-reviewer already approved the change; your job is quality, not scope.
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.
- 5d ago First seen · 73 lines · 70 tokens per session scan A 1e5c1ba3bafb
cadence-code-reviewer is an agent published in the GitHub repository sentasity/cadence (1 stars, last pushed 10d ago), licensed MIT. It adds 70 tokens to every session and 894 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
code-reviewer
The pipeline's post-implementation review-and-fix pass — reviews the diff a task's implementation just produced, proves each candidate defect before touching it, fixes the confirmed ones inside the plan's Touches, runs the project's own build and tests, and amends the implementation commit.
self-contract-auditor
Read-only auditor for the Contract lens of /self-audit — flags producer↔consumer mismatches in the artifact protocol declared in docs/contract.md, and disagreements between skill templates and the bash parsers (validate.sh, roadmap.sh).
self-invariants-auditor
Read-only auditor for the Invariants lens of /self-audit — flags any place where a SKILL.md or bash helper violates an invariant declared in CLAUDE.md § "Invariants — don't break these when editing skills".
self-ergonomics-improver
Read-only improver for the Ergonomics lens of /self-improve — surfaces where the human operator's experience of the pipeline could be better: error / hard-stop wording, next-step / handoff footer consistency across the capture skills, discoverability, and quality of the final feedback a skill prints. Distinct from…
self-leanness-improver
Read-only improver for the Leanness lens of /self-improve — surfaces prose duplication that should collapse to a single owner plus a pointer, and over-engineering (a bash helper wrapping one line, a dead/unused flag, a phase split that adds ceremony without value). Everything it flags is currently correct and…
self-clarity-improver
Read-only improver for the Clarity lens of /self-improve — surfaces places where a SKILL.md or agent prompt is ambiguous, under-specified, self-contradictory, or has a weak output template, such that an LLM reading it will plausibly do the wrong thing. Nothing here is a rule violation (that is /self-audit) — this is…