cadence-spec-reviewer

cadence-spec-reviewer is an agent for Claude Code from sentasity/cadence. It costs 0 tokens per session (1,991 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 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,991 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 $0.00000 $0.01991
Opus 5.5 $0.00000 $0.00796
Sonnet 5.5 $0.00000 $0.00398
Haiku 4.5 $0.00000 $0.00199

Measured 26d ago against content hash 5ac9d32fe5b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, 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 26d 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 · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 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 listed in the task's Reads: block.
  • The plan's style: full-code or decisions (from the plan overview's Plan style line; full-code when the plan has none).
  • The plan's Global Constraints section, when the plan has one.
  • The Review Focus entries pinned in this lane's tasks, when there are any.
  • The implementer's Tests: evidence.

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 Touches: list (Files: on a legacy-format plan), that's a gap. It could be an extraneous edit or could mean the list was incomplete; surface it either way.
  3. The diff matches what the plan fixed, per the plan's style.
    • Full-code plans: if the task block shows the exact code to write, the diff matches 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.
    • Decision plans: the decisions are binding and the rest is the implementer's call. A gap is any difference from: a signature the task produces (name, parameters, return type), including every Produces: entry in its Interfaces block; file placement; a test the plan names, or any of its assertions and expected values; a value the design pins, as the plan states it; an algorithm body or exact copy the plan spells out. The exported surface matches the plan: nothing missing, and no public symbol the plan doesn't declare. Private helpers, internal structure, local names, and idiom inside the Touches: files are free; they belong to cadence-code-reviewer.
  4. Commands ran and produced expected output. Compare the implementer's Tests: evidence against each run step's Expected line. A run step with no evidence, or evidence that doesn't match, is a gap. Don't re-run the suite yourself.
  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).
  7. Global Constraints. The diff violates no line of the plan's Global Constraints. A violation is a spec gap, cited to the constraint line.
  8. Review Focus pins. For each Review Focus entry pinned in this lane's tasks, the diff carries the pin (the test assertion, or the run step's command) and the Tests: evidence shows it passing.

Read the full file on GitHub · 95 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. 26d ago Changed · +15 lines 5ac9d32fe5b1
  2. 1mo ago Changed · +8 lines 87a10ff73566
  3. 1mo ago Changed · +1 lines · -76 tokens per session bc7efb50a60c
  4. 2mo 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 26d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,991 tokens. 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

cadence-spec-reviewer compared with agents from other repositories

cadence-spec-reviewer next to 6 agents from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
cadence-spec-reviewersentasity/cadenceAgent126d agoMITA0Claude Code
code-reviewerSpaiR/task-pipelineAgent71mo agoMITA71Claude Code
self-invariants-auditorSpaiR/task-pipelineAgent71mo agoMITA89Claude Code
self-leanness-auditorSpaiR/task-pipelineAgent71mo agoMITA116Claude Code
self-docs-sync-auditorSpaiR/task-pipelineAgent71mo agoMITA94Claude Code
reviewer-anthropicshindo107/plan-build-reviewAgent25d agoMITA47Claude Code
reviewerdonald-ada/workinggeniusAgent64d agoMITA70Claude Code