review-skill-improver

review-skill-improver is a skill for Claude Code from existential-birds/beagle. It costs 35 tokens per session (1,486 once invoked), scanned A, original, Apache-2.0.

A review tool that studies recorded feedback about another review skill and recommends improvements. It compares accepted and rejected decisions, their sources, and the reasons given for them.

In plain words
What is it for?
Loading and validating feedback logs, counting decisions by rule source, measuring rejection patterns, and suggesting specific changes to improve review accuracy.
Why use it?
It reveals rules that reject too many valid cases and gaps where important problems were missed, using the complete feedback record before making recommendations.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter.

Part of the beagle-core plugin — 19 skills shipped together

Good fit Loading and validating feedback logs, counting decisions by rule source, measuring rejection…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/existential-birds/beagle/review-skill-improver
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 existential-birds/beagle --skill review-skill-improver
Clone the repo
git clone --depth 1 https://github.com/existential-birds/beagle

Made for: Claude Code.

Or install beagle-core, the plugin that ships this one along with the rest of its 19 skills.

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 review-skill-improver

README.md
[![agentmods](https://agentmods.dev/badge/skills/existential-birds/beagle/review-skill-improver.svg)](https://agentmods.dev/skills/existential-birds/beagle/review-skill-improver)
Your own site
<a href="https://agentmods.dev/skills/existential-birds/beagle/review-skill-improver"><img src="https://agentmods.dev/badge/skills/existential-birds/beagle/review-skill-improver.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,486 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 $0.00035 $0.01486
Opus 5 $0.00017 $0.00743
Sonnet 5 $0.00007 $0.00297
Haiku 4.5 $0.00003 $0.00149

Measured 7d ago against content hash d2cdfc550d23, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

review-skill-improver 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 7d 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.

plugins/beagle-core/skills/review-skill-improver/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review Skill Improver

Purpose

Analyzes structured feedback logs to:

  1. Identify rules that produce false positives (high REJECT rate)
  2. Identify missing rules (issues that should have been caught)
  3. Suggest specific skill modifications

Input

Feedback log in enhanced schema format (see the review-feedback-schema skill).

Hard gates

Run in order; do not emit the final Review Skill Improvement Report until each gate passes.

  1. Input on record — The log is loaded from a stated path in the repo or from an attached artifact, not from memory or paraphrase. Pass: the report header or Summary names that path or states “attached feedback blob” with byte/line count.
  2. Schema / shape — Entries match the enhanced schema (rule_source, verdict, rationale, etc. per the review-feedback-schema skill). Pass: either all rows parse, or skipped malformed rows are counted and listed by row index (not silently dropped).
  3. Aggregation before thresholds — Complete Step 1 (per–rule_source totals, ACCEPT vs REJECT, rejection rate, rejection rationales) for the full parsed set before labeling any rule “high-rejection” or writing recommendations. Pass: Summary includes “Unique rules triggered” consistent with the aggregation table.
  4. Evidence-bound recommendations — Every recommendation includes at least one concrete evidence pointer (log row(s), or file:line + short quote) before Proposed Fix. Pass: Evidence is non-empty for each recommendation.

Analysis Process

Step 1: Aggregate by Rule Source

For each unique rule_source:
  - Count total issues flagged
  - Count ACCEPT vs REJECT
  - Calculate rejection rate
  - Extract rejection rationales

Step 2: Identify High-Rejection Rules

Rules with >30% rejection rate warrant investigation:

  • Read the rejection rationales
  • Identify common themes
  • Determine if rule needs refinement or exception

Read the full file on GitHub · 200 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. 7d ago First seen · 200 lines · 35 tokens per session scan A d2cdfc550d23

Subscribe to this mod's changes

review-skill-improver is a skill published in the GitHub repository existential-birds/beagle (80 stars, last pushed 28d ago), licensed Apache-2.0. It adds 35 tokens to every session and 1,486 once invoked, about $0.0002 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 2026-08-30.

Related

Other skills, from other repositories