spec-reviewer

spec-reviewer is an agent for Claude Code from jhlee0409/omni-harness-kit. It costs 101 tokens per session (415 once invoked), scanned A, original, MIT.

A pull-request reviewer that compares code changes with the active specification, which is the written description of what the change must do. It reports whether the work matches, exceeds, or falls short of that scope.

In plain words
What is it for?
Use it when reviewing a pull request against its specification and plan. It checks changed files and provides evidence for delivered or missing work.
Why use it?
It catches unrequested additions and plan tasks that were claimed as complete but were not actually implemented. Pull requests without a specification are skipped.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the harness-kit plugin — 18 skills, 28 agents, 2 hooks shipped together

Good fit Use it when reviewing a pull request against its specification and plan. It checks changed files and provides evidence for delivered or missing work.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jhlee0409/omni-harness-kit/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/jhlee0409/omni-harness-kit

Made for: Claude Code.

Or install harness-kit, the plugin that ships this one along with the rest of its 18 skills, 28 agents, 2 hooks.

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 spec-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/spec-reviewer/github.svg)](https://agentmods.dev/agents/jhlee0409/omni-harness-kit/spec-reviewer)
Your own site
<a href="https://agentmods.dev/agents/jhlee0409/omni-harness-kit/spec-reviewer"><img src="https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/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 spec-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/jhlee0409/omni-harness-kit/spec-reviewer"><img src="https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/spec-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 415 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 $0.00101 $0.00415
Opus 5 $0.00051 $0.00208
Sonnet 5 $0.00020 $0.00083
Haiku 4.5 $0.00010 $0.00042

Measured 10d ago against content hash e886d5bb99c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

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 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.

agents/spec-reviewer.md · 32 lines

What it actually says

You are the spec reviewer. Check a PR's diff against its spec — delivered scope, silent over-reach, and skipped-but-claimed plan tasks.

Procedure

  1. Resolve the spec by branch → slug (specs/<date>-<slug>/). If none, NO-OP: say "no spec for this PR — nothing to review" and stop. Never block a spec-less PR.
  2. Read the spec triplet (spec / plan / context) — the required scope + plan tasks.
  3. Diff vs spec: git diff the PR. For each plan task — delivered? For the diff — does it stay within the spec's "In" scope, or add unrequested work?
  4. Claimed-vs-done: if the PR says it closes a plan task, confirm the diff actually implements it (not just checks the box).

Output (BLUF)

  • Verdict: MATCHES SPEC / EXCEEDS (list the out-of-scope additions) / SHORT (list unmet plan tasks) / NO SPEC (no-op).
  • Per task: delivered / missing, with file:line evidence.

Constraints

  • A spec-less PR is NOT a finding — NO-OP gracefully.
  • Cite the diff and the spec; don't infer delivery from the PR description.
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. 10d ago First seen · 32 lines · 101 tokens per session scan A e886d5bb99c3

Subscribe to this mod's changes

spec-reviewer is an agent published in the GitHub repository jhlee0409/omni-harness-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 101 tokens to every session and 415 once invoked, about $0.0005 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

doc-sync-scan

Cold doc-sync judge — the commit door's scope-overload valve. Given a diff and a mechanically enumerated scan scope (reverse-citer read-set + grep-hit files + link-target files), judges each scope doc against the diff's claims and runs a diff-scoped new-assertion residual, returning stale-doc candidates for the…

RockyHong/super-bootstrap · 0 tokens

verifier

Use proactively after builder or architect completes any task that edited files. Reviews the diff against the task's intent before the result is accepted. Read-only reviewer; never fixes anything itself.

Adityaraj0421/gearbox · 39 tokens

wisp-self-test

A canary subagent bundled with wisp-agentdiff that verifies the WorktreeCreate / WorktreeRemove hooks are wired correctly end-to-end. Use this when the user asks to "test wisp-agentdiff", "verify wisp-agentdiff", "check if wisp-agentdiff is working", or after a fresh /plugin install wisp-agentdiff to confirm the…

Samuel0101010/wisp-agentdiff · 108 tokens

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…

damusix/atomic-claude · 169 tokens

symfony-security-auditor

Read-only security audit of Symfony authentication and authorization: firewalls, accesscontrol, voters, API Platform security, rate limiting, CSRF, password hashing, and input validation. Use proactively after changes to security.yaml, voters, controllers, forms, or API resources.

dev-toolings/superpowers-symfony · 60 tokens

code-simplifier

Simplifies and refines code for clarity, consistency, and maintainability while preserving all functionality. Applies safe local simplifications (local renames, dead code, unnecessary nesting) directly and proposes structural changes for approval. Focuses on recently modified code unless instructed otherwise; not for…

oprogramadorreal/optimus-claude · 66 tokens