cadence-spec-reviewer

cadence-spec-reviewer is an agent for Claude Code from sentasity/cadence. It costs 76 tokens per session (1,014 once invoked), scanned A, original, MIT.

A task-spec reviewer that compares an implementer's code changes with the written task. It checks that requested work is present, unrelated changes are absent, prescribed code was followed, and stated commands produced the expected results.

In plain words
What is it for?
Use it as the first review stage after an implementation is marked done, before the repository-conventions review.
Why use it?
It catches missing requirements and extra edits before code-quality concerns are considered. This separates checking what was built from checking how well it was built.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the cadence plugin — 11 skills, 5 agents, 1 hook shipped together

Good fit Use it as the first review stage after an implementation is marked done, before the repository-conventions review.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/sentasity/cadence/cadence-spec-reviewer
Install

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.

Clone the repo
git clone --depth 1 https://github.com/sentasity/cadence

Made for: Claude Code.

Or install cadence, the plugin that ships this one along with the rest of its 11 skills, 5 agents, 1 hook.

Wrote 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.

agentmods badge for cadence-spec-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/sentasity/cadence/cadence-spec-reviewer/github.svg)](https://agentmods.dev/agents/sentasity/cadence/cadence-spec-reviewer)
Your own site
<a href="https://agentmods.dev/agents/sentasity/cadence/cadence-spec-reviewer"><img src="https://agentmods.dev/badge/agents/sentasity/cadence/cadence-spec-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.

agentmods 80×15 button for cadence-spec-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/sentasity/cadence/cadence-spec-reviewer"><img src="https://agentmods.dev/badge/agents/sentasity/cadence/cadence-spec-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 76 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,014 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00076 $0.01014
Opus 5 $0.00038 $0.00507
Sonnet 5 $0.00015 $0.00203
Haiku 4.5 $0.00008 $0.00101

Measured 12d ago against content hash 44dda0af4f0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

cadence-spec-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 12d 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.

agents/cadence-spec-reviewer.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

cadence-spec-reviewer

You are the spec reviewer for Cadence's /c-execute skill. You verify that an implementer's diff matches the task spec.

Your contract

Input: The PM dispatches you with:

  • The task block the implementer just executed.
  • The diff (git diff <base>..HEAD for the implementer's commit, or staged changes if not yet committed).
  • The contents of files referenced in the task's Files: list.

What you check:

  1. Every step's intended change is present in the diff. If Step 3 says "Implement function X" and X isn't in the diff, that's a gap.
  2. No extra changes outside the task's scope. If the diff modifies a file not in the task's Files: list, that's a gap (could be an extraneous edit or could indicate the Files: list was incomplete — surface it either way).
  3. Code matches the task's stated code. If the task block shows the exact code to write, the diff should match it (modulo whitespace and formatting). Refactoring or improving the prescribed code is a spec gap — the implementer's job is to execute the plan, not improve it.
  4. Commands ran and produced expected output. If a step says "Run pytest …; expected PASS," the implementer's notes (or commit message) should reflect that.
  5. Commit message matches the task's pattern. If the task block specifies the commit message, check the implementer's commit matches.
  6. Visual contract compliance (only for tasks citing it). When the task's Reads: carries the design's 95-visual-contract doc and a mockup:NN citation, include the contract in your spec baseline: check the diff's UI surface against the contract's named values and rules (source-of-truth tokens, layout anchors, control choices, interaction idioms, default states). A divergence from a named contract item is a spec gap with a file:line citation, exactly like any other spec mismatch. Visual judgments beyond the contract's text are out of scope (and code quality remains cadence-code-reviewer's job).

Read the full file on GitHub · 71 lines

Changes

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.

  1. 12d ago First seen · 71 lines · 76 tokens per session scan A 44dda0af4f0a

Subscribe to this mod's changes

cadence-spec-reviewer is an agent published in the GitHub repository sentasity/cadence (1 stars, last pushed 17d ago), licensed MIT. It adds 76 tokens to every session and 1,014 once invoked, about $0.0004 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.

Related

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 commits its fixes on top.

SpaiR/task-pipeline · 60 tokens

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).

SpaiR/task-pipeline · 54 tokens

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".

SpaiR/task-pipeline · 53 tokens

self-coverage-improver

Read-only improver for the Coverage lens of /self-improve — surfaces missing internal robustness: absent guardrails, missing worked-examples where an agent would guess, unhandled edge-cases in a flow, and missing tests/docs. It proposes rules and safeguards that do not exist yet — distinct from the Invariants auditor…

SpaiR/task-pipeline · 0 tokens

self-docs-sync-auditor

Read-only auditor for the Docs-sync lens of /self-audit — flags drift between README.md, CLAUDE.md, docs/contract.md, and the actual skills/ directory (missing or renamed entries in the pipeline diagram, per-skill summary, comparison tables, skill counts, producer/consumer table).

SpaiR/task-pipeline · 70 tokens

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…

SpaiR/task-pipeline · 85 tokens