reviewer-agent

reviewer-agent is a skill for Claude Code, Codex from Tholem-AI/Tholem-Hermes-Kit. It costs 23 tokens per session (1,075 once invoked), scanned A, original, MIT.

A final review process for checking completed coding work before it is merged or released. It looks at correctness, safety, policy fit, evidence, and the risk of regressions.

In plain words
What is it for?
Use it after implementing a bug fix, refactor, or cleanup. It can guide checks such as searching for removed code, testing the application, reviewing documentation, and deciding whether the work is ready to release.
Why use it?
It helps catch unresolved problems and weak verification before a change is treated as finished.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it after implementing a bug fix, refactor, or cleanup. It can guide checks such as searching for removed code, testing the application, reviewing documentation, and deciding whether the work is ready to release.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tholem-ai/tholem-hermes-kit/reviewer-agent
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.

Any agent
npx skills add Tholem-AI/Tholem-Hermes-Kit --skill reviewer-agent
Clone the repo
git clone --depth 1 https://github.com/Tholem-AI/Tholem-Hermes-Kit

Made for: Claude Code, Codex.

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 reviewer-agent

README.md
[![agentmods](https://agentmods.dev/badge/skills/tholem-ai/tholem-hermes-kit/reviewer-agent/github.svg)](https://agentmods.dev/skills/tholem-ai/tholem-hermes-kit/reviewer-agent)
Your own site
<a href="https://agentmods.dev/skills/tholem-ai/tholem-hermes-kit/reviewer-agent"><img src="https://agentmods.dev/badge/skills/tholem-ai/tholem-hermes-kit/reviewer-agent/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 reviewer-agent

Your own site · 80×15
<a href="https://agentmods.dev/skills/tholem-ai/tholem-hermes-kit/reviewer-agent"><img src="https://agentmods.dev/badge/skills/tholem-ai/tholem-hermes-kit/reviewer-agent.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,075 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 $0.00023 $0.01075
Opus 5 $0.00012 $0.00537
Sonnet 5 $0.00005 $0.00215
Haiku 4.5 $0.00002 $0.00108

Measured 12d ago against content hash e4d6d43eabc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

reviewer-agent 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/reviewer-agent/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

reviewer-agent

Overview

Verify implementation quality, policy alignment, and release readiness before closure. The reviewer is the final gate — it presents findings ordered by severity and recommends whether work is ready for release.

When to Use

  • Use after execution phase produces completed slices with evidence.
  • Use before declaring work complete or merging changes.
  • Don't use for mid-execution checks — those belong to the executor's validation gates.

Slice Execution Review

When reviewing a specific slice of completed work (dead code removal, refactoring, bug fix), see references/slice-execution-review.md for the full verification workflow: search for removed symbols, check each removal site, verify line count, live-test the application, and cross-check documentation.

Operating contract

  1. Prioritize correctness, safety, and regression risk.
  2. Validate evidence quality and contradiction-free state.
  3. Validate documentation continuity outcomes, but do not assume primary documentation ownership.
  4. Route documentation policy/content updates through the documentation-maintainer skill.
  5. Require explicit remediation for any unresolved blocker.
  6. Verify docs/File-Structure-Reference.md and docs/Project-Constraints.md are updated when implementation scope impacts them.

Steps

  1. Receive executor-agent handoff outputs (one or more, if parallel slices were used).
  2. Verify each slice against the original plan:
    • Were all planned changes applied?
    • Were all validation gates satisfied?
    • Is evidence complete and traceable?
  3. Check for correctness issues: bugs, type errors, logic flaws, missing edge cases.
  4. Check for safety issues: exposed secrets, unsafe defaults, privilege escalation paths.
  5. Check for regression risk: unintended side effects on unaffected modules.
  6. Verify documentation continuity: docs/File-Structure-Reference.md, docs/Project-Constraints.md, and project READMEs are aligned.
  7. Present findings ordered by severity with a release-readiness recommendation.
  8. Produce a handoff output following the schema below.

Read the full file on GitHub · 100 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 100 lines · 23 tokens per session scan A e4d6d43eabc9

Subscribe to this mod's changes

reviewer-agent is a skill published in the GitHub repository Tholem-AI/Tholem-Hermes-Kit (2 stars, last pushed 3mo ago), licensed MIT. It adds 23 tokens to every session and 1,075 once invoked, about $0.0001 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.