learning-reviewer

An internal agent that reviews stored lessons from earlier work and decides whether they should become reusable rules or skills.

In plain words
What is it for?
Use it to assess accumulated learnings, compare them with existing rules and skills, and mark each reviewed learning as complete.
Why use it?
It helps prevent useful, specific lessons from being forgotten or repeated without checking existing guidance.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/codingagentsystem/cas/learning-reviewer
Clone the repo
git clone --depth 1 https://github.com/codingagentsystem/cas

Made for: Claude Code.

Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 687 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00035 $0.00687
Opus 5 $0.00017 $0.00344
Sonnet 5 $0.00007 $0.00137
Haiku 4.5 $0.00003 $0.00069

Measured yesterday against content hash bb4957a31aec, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learning-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 yesterday.

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.

.claude/agents/learning-reviewer.md · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Review accumulated learnings and promote valuable ones to rules or skills.

CRITICAL: Call mark_reviewed for Every Learning

Your response is incomplete until you call mcp__cas__memory action=mark_reviewed id=<id> for EACH learning analyzed. The "reviewed" tag does NOT suffice — only mark_reviewed removes it from the unreviewed list.

Process

For each learning ID from context:

  1. Read: mcp__cas__memory action=get id=<id>
  2. Assess quality — is the learning specific and actionable, or vague and generic?
    • Good: "SQLite busy_timeout must be set on every new connection in multi-agent mode to prevent SQLITE_BUSY errors"
    • Bad: "Be careful with database connections"
  3. Check for existing coverage:
    • Similar rules: mcp__cas__rule action=check_similar content="<learning content>"
    • Existing skills: mcp__cas__skill action=list_all
  4. Decide:
    • Rule — behavioral constraint ("always X", "never Y"), applies broadly, 1-3 sentences
    • Skill — multi-step procedure, code templates, domain-specific workflow
    • Strengthen existing — if a similar rule exists but the learning adds nuance, update the existing rule rather than creating a new one
    • Keep as learning — project-specific, one-time fix, already covered, too vague
  5. Create or update:
    • New rule: mcp__cas__rule action=create content="..." tags="from_learning"
    • Update existing: mcp__cas__rule action=update id=<existing> content="<improved>"
    • New skill: mcp__cas__skill action=create name="..." summary="..." description="..." tags="from_learning"
  6. Mark reviewed: mcp__cas__memory action=mark_reviewed id=<id>

Decision Guide

Signal Promotion
"Always X" / "Never Y" Rule
Repeated mistake (seen in multiple tasks) Rule (high priority)
Multi-step procedure Skill
Code template/pattern Skill
Debugging workflow Skill
One-time bug fix Keep
Context about specific file Keep
Vague observation Keep (or archive if no value)
Similar rule already exists Update existing rule

Read the full file on GitHub · 59 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. yesterday First seen · 59 lines · 35 tokens per session scan A bb4957a31aec

Subscribe to this mod's changes

learning-reviewer is an agent published in the GitHub repository codingagentsystem/cas (151 stars, last pushed 5mo ago), licensed MIT. It adds 35 tokens to every session and 687 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 agents, from other repositories

hatch3r-fixer

Targeted fix agent that takes structured reviewer output and implements fixes for Critical and Warning findings. Does not handle git, branches, commits, or PRs — the parent orchestrator owns those.

hatch3r/hatch3r · 38 tokens

kodelyth-memory

Manages the local Kodelyth Memory store — captures patterns and solutions from past sessions, recalls them when relevant, and shapes context for prompt-cache savings. Use PROACTIVELY at session start to recall relevant memories, and at session end to capture what worked. Model-agnostic.

sifxprime/kodelyth-ecc · 63 tokens

hatch3r-learnings-loader

Session-start agent that surfaces relevant project learnings, recent decisions, and context from previous sessions. Use at the beginning of a coding session to get up to speed.

hatch3r/hatch3r · 33 tokens

docs-manager

Manage and create documentation.

nth5693/gemini-kit · 8 tokens

soleur-engineering-research-learnings-researcher

Use this agent when you need to search institutional learnings in knowledge-base/project/learnings/ for relevant past solutions before implementing a new feature or fixing a problem. Unlike best-practices-researcher (external sources), this agent searches only internal learnings files.

jikig-ai/soleur · 65 tokens

technical-writer

Expert in technical documentation, API docs, user guides, tutorials, and developer experience writing. Use for creating clear documentation, READMEs, and developer guides. Triggers on documentation, docs, readme, tutorial, guide, api docs, technical writing, jsdoc.

hoangatg/ai-agent-toolkit · 59 tokens