a-self-learner

a-self-learner is a skill for Claude Code, Codex from imisic/claude-marketplace. It costs 17 tokens per session (3,548 once invoked), scanned A, original, MIT.

A feedback-loop skill that turns repeated findings from project reviews into proposed updates to rules or review skills. It can analyse review history without changing files by default.

In plain words
What is it for?
Use it to inspect review history, identify recurring or chronic issues, and prepare rule or skill changes for explicit approval.
Why use it?
It helps prevent the same class of problem from appearing repeatedly by turning recurring lessons into future checks.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: mentions CLAUDE.md.

Part of the dev-workflow-forge plugin — 4 skills shipped together

Good fit Use it to inspect review history, identify recurring or chronic issues, and prepare rule or skill changes for explicit approval.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/imisic/claude-marketplace/a-self-learner
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 imisic/claude-marketplace --skill a-self-learner
Clone the repo
git clone --depth 1 https://github.com/imisic/claude-marketplace

Made for: Claude Code, Codex.

Or install dev-workflow-forge, the plugin that ships this one along with the rest of its 4 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 a-self-learner

README.md
[![agentmods](https://agentmods.dev/badge/skills/imisic/claude-marketplace/a-self-learner/github.svg)](https://agentmods.dev/skills/imisic/claude-marketplace/a-self-learner)
Your own site
<a href="https://agentmods.dev/skills/imisic/claude-marketplace/a-self-learner"><img src="https://agentmods.dev/badge/skills/imisic/claude-marketplace/a-self-learner/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 a-self-learner

Your own site · 80×15
<a href="https://agentmods.dev/skills/imisic/claude-marketplace/a-self-learner"><img src="https://agentmods.dev/badge/skills/imisic/claude-marketplace/a-self-learner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,548 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 $0.00017 $0.03548
Opus 5 $0.00009 $0.01774
Sonnet 5 $0.00003 $0.00710
Haiku 4.5 $0.00002 $0.00355

Measured 10d ago against content hash c8cb8d27d328, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

a-self-learner 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.

The scan reads SKILL.md. This mod also ships 2 executable files (references/capture-finding.sh, scripts/migrate-review-log-v2.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/dev-workflow-forge/skills/a-self-learner/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Self-Learner: Review → Rule/Skill Feedback Loop

Closes the loop between review skills and rule/skill files. When a project review catches the same class of issue repeatedly, this skill proposes a preventive update (a new rule, a new preflight check, or a whitelist entry) and hands it off to a-rules-optimizer or a-review-optimizer for application.

Input: optional flags

  • --dry-run (default): analyze and propose, never write
  • --apply: after each proposal, ask user, apply on approval
  • --since YYYY-MM-DD: only consider findings from this date forward
  • --threshold N: override recurrence threshold (default 3 for recurring, 5 for chronic)

If the project has no .claude/reviews/ directory yet, the skill reports "no history to learn from" and offers to scaffold the convention (see references/review-log-schema.md).


Core Principles

Propose, never silently write. Every rule/skill change must be shown to the user as a diff with rationale, then applied only after explicit approval. Propose only; never auto-apply and never auto-commit. A proposal workflow is not commit authorization, whatever your project or global commit rules say.

Delegate writes to the other optimizers. This skill never edits rule files or review SKILL.md directly. It generates a structured proposal and invokes a-rules-optimizer (for rule writes) or a-review-optimizer (for preflight/agent writes). Keeps each skill's scope tight.

Evidence > opinion. A recurrence claim needs ≥ N findings of the same category across distinct dates. "Feels recurring" is not good enough; the cluster must survive the grouping algorithm in references/recurrence-detection.md.

Record rejections. Proposals the user declines get logged to rejected-proposals.md with the reason. Next run shouldn't re-raise the same rejection: only surface if new evidence appears (e.g., the issue recurred another 5 times since rejection).

Per-project scope. Each project owns its own .claude/reviews/ directory. The skill does not cross-pollinate learnings between projects (that's a future extension; for now, deliberate isolation keeps project conventions separate).

Read the full file on GitHub · 202 lines

Files

What ships with it

6 files 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. 10d ago First seen · 202 lines · 17 tokens per session scan A c8cb8d27d328

Subscribe to this mod's changes

a-self-learner is a skill published in the GitHub repository imisic/claude-marketplace (2 stars, last pushed 9d ago), licensed MIT. It adds 17 tokens to every session and 3,548 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.

Related

Other skills, from other repositories

tokf-discover

Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.

mpecan/tokf · 24 tokens

dashiai-ppt

A presentation-making add-on that creates an HTML slide deck from preset visual page designs. The result can open offline in a browser and can be exported as a PowerPoint or PDF file.

huangrichao2020/pretty-skills · 62 tokens

skillnote

Self-hosted skill registry for OpenClaw. Stores procedures your team writes (name, description, body), syncs them to disk before each task, and collects which-helped/which-failed signals from the agent so the registry improves over time.

luna-prompts/skillnote · 54 tokens

xiaohongshu-image-creator

An image-making assistant for Xiaohongshu, a Chinese social platform for lifestyle, product, and educational posts. It creates vertical covers and supporting images matched to the post’s topic, audience, and visual style.

huangrichao2020/pretty-skills · 121 tokens

sansheng-distill

A book and text summarizer that creates one self-contained HTML page with five sections: an overview, chapter notes, the book’s central idea, an action checklist, and questions for judging its reliability. The page includes an embedded Mermaid mind map and works offline without a web server.

huangrichao2020/pretty-skills · 108 tokens

cross-campaign

Discover and reference other camps, projects, and files across camp boundaries. Use when the user mentions another camp or campaign by name, references work done "in another project/camp", or needs to find/copy/compare code across camps.

Obedience-Corp/festival · 52 tokens