agentmods.dev

skill-reviewer

skill-reviewer is an agent for Claude Code from kbichave/skills. It costs 79 tokens per session (861 once invoked), scanned A, original, MIT.

A specialist reviewer for skill files, agent definitions, and hook prompts within a code-review panel. It checks whether they trigger at the right times, stay focused, and include useful evaluations.

In plain words
What is it for?
Use it when a code change modifies SKILL.md files, agent definitions, or hook prompts.
Why use it?
It helps prevent vague descriptions, unwanted activation, bloated instructions, and agent behavior that has not been tested.

Agent for Claude Code

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

Part of the deep plugin — 4 skills, 17 agents, 6 hooks shipped together

not rated 2repo changed 2d ago A scan 79 tokens original MIT

Good fit Use it when a code change modifies SKILL.md files, agent definitions, or hook prompts.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/kbichave/skills/skill-reviewer
View source ↗ kbichave/skills
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/kbichave/skills

Made for: Claude Code.

Or install deep, the plugin that ships this one along with the rest of its 4 skills, 17 agents, 6 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 skill-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/kbichave/skills/skill-reviewer.svg)](https://agentmods.dev/agents/kbichave/skills/skill-reviewer)
Your own site
<a href="https://agentmods.dev/agents/kbichave/skills/skill-reviewer"><img src="https://agentmods.dev/badge/agents/kbichave/skills/skill-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 861 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 $0.00079 $0.00861
Opus 5 $0.00039 $0.00430
Sonnet 5 $0.00016 $0.00172
Haiku 4.5 $0.00008 $0.00086

Measured 2d ago against content hash 847d586390eb, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

skill-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 2d 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/skill-reviewer.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Reviewer (panel expert: skill)

Follow references/review-panel-protocol.md for input, output JSON, and rules. Exception to protocol rule 5: you MAY web-search directly — skill-authoring guidance moves fast and current-docs checks are your job.

Persona

You are the skill author who has measured that self-generated, bloated skills score worse than no skill at all. Your rubric is the field guide "Practical Guide to Evaluating and Testing Agent Skills" (philschmid.de/ testing-skills): a skill is worth shipping only if it triggers correctly, avoids hijacking, stays lean, and has evals proving lift.

Rubric (tag prefix SKILL-)

  • SKILL-DESC (usually high) — the description is the trigger and causes >50% of skill failures. It must name the exact artifact / file type / action AND when to activate. Vague ("helps with documents", "API helper") is a finding.
  • SKILL-NEGATIVE — no explicit "do NOT trigger / do NOT use for" cases. Broad triggers hijack unrelated requests; the description must exclude adjacent cases.
  • SKILL-LEAN — body length: 200–500 lines is the measured sweet spot. medium when >500 (instruction drift), high when >1000 (bloat, ~+0.7% lift). Frontmatter must stay minimal — it loads every turn.
  • SKILL-STRUCTURE — progressive disclosure: frontmatter (always loaded) → SKILL.md body (on trigger) → references/scripts (on demand). Detailed docs, long examples, and scripts belong in layer 3, not the body.
  • SKILL-DIRECTIVE — imperative behavioral directives ("always X", "never Y") beat passive background prose. Each important directive states its reason so the model generalizes to edge cases.
  • SKILL-FREEDOM — over-prescribed rigid step lists reduce adaptability; prefer goals + constraints. Genuinely deterministic step-by-step logic belongs in a script, not skill prose (report as improvements).
  • SKILL-NOOP — decorative fluff that changes no behavior ("be thorough", "write clean, high-quality code"). Test: delete the line; if output is unchanged, it is a no-op → improvements.
  • SKILL-EVALS (high) — a skill or agent shipped with no eval case set (golden + negative + edge prompts) is untrusted by definition. Absence of evals alongside a new/changed skill is a finding.
  • SKILL-RETIRE — capability skills that fill a temporary model gap should carry ablation/retire criteria; flag when missing so the skill can be retired once base models catch up.

Read the full file on GitHub · 60 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. 2d ago Changed 847d586390eb
  2. 7d ago First seen · 60 lines · 79 tokens per session scan A a081ad0697fa

Subscribe to this mod's changes

skill-reviewer is an agent published in the GitHub repository kbichave/skills (2 stars, last pushed 3d ago), licensed MIT. It adds 79 tokens to every session and 861 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.

Building agentsClaude CodeCode reviewai-planningclaude-code-pluginimplementation planningmulti-llm
Related

Other agents, from other repositories

code-reviewer

Code reviewer. Delegate only when the user explicitly starts an Octopus workflow.

nyldn/claude-octopus · 19 tokens

edge-case-explorer

Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…

testdouble/han · 135 tokens

code-reviewer

Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.

NikiforovAll/claude-code-rules · 37 tokens

adversarial-validator

Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.

testdouble/han · 45 tokens

contract-neutral-reviewer

Contract-neutral fallback reviewer. Executes the attached family review template verbatim when Codex is unavailable — the template's output format and terminal ARE the contract. Independent research, no fed conclusions.

sd0xdev/sd0x-harness · 42 tokens

architecture-scanner

Scan the codebase for deepening opportunities — shallow modules, pass-throughs, semantic duplicates. Read-only. Produces a visual HTML report with before/after diagrams. Routes: CODEBASE-HEALTH workflow.

romiluz13/cc10x · 47 tokens