self-learning

A rule for improving an agent skill after an audit finds a bug that its checklist should have caught. It updates the checklist with a short, specific check and keeps the instructions from growing unnecessarily.

In plain words
What is it for?
Use it immediately after reporting or fixing audit findings to identify the missed check, sharpen an existing instruction, or add one when needed.
Why use it?
It helps prevent the same kind of mistake from recurring. The fix is recorded in the skill's process, not only in the code that had the bug.

Skill for Claude CodeCodex

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 skills/grinv/mal-mcp/self-learning
Any agent
npx skills add Grinv/mal-mcp --skill self-learning
Clone the repo
git clone --depth 1 https://github.com/Grinv/mal-mcp

Made for: Claude Code, Codex.

Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 239 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin 100% copy Near-identical to another mod 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 $0.00041 $0.00239
Opus 5 $0.00020 $0.00120
Sonnet 5 $0.00008 $0.00048
Haiku 4.5 $0.00004 $0.00024

Measured 2d ago against content hash cee11dd5c939, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

self-learning 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.

Origin

This is a copy

100% identical to self-learning — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/self-learning/SKILL.md · 22 lines

What it actually says

Self-learning — close the gap in the skill that missed it

For each confirmed finding from an audit/check pass:

  1. Identify which skill's checklist should have caught this — don't stop at fixing the code.
  2. If an existing bullet already covers this general class of check, sharpen/specialize it with the missed detail — don't add a new bullet next to it.
  3. Only add a brand-new bullet if nothing existing is even adjacent.
  4. Keep additions to 1-2 lines. No walkthroughs, no multi-sentence examples — these files compound over many passes; a short parenthetical example is fine, a paragraph is not.
  5. If a skill file is drifting toward bloat (bullets turning into short essays), that's a signal to prune/merge, not to keep appending — periodically re-read the whole file and tighten instead of only adding.
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 First seen · 22 lines · 41 tokens per session scan A cee11dd5c939

Subscribe to this mod's changes

self-learning is a skill published in the GitHub repository Grinv/mal-mcp (2 stars, last pushed 9d ago), licensed MIT. It adds 41 tokens to every session and 239 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to self-learning, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

live-audit

Audit anilist-mcp-server — build/test/lint gate, live MCP tool edge-case sweep (input validation, not-found paths, mutations with capture/revert), source-level code review, and docs/metadata consistency. Use when asked to test/audit the published or just-fixed anilist-mcp-server package, hunt for bugs/edge cases, or…

Grinv/anilist-mcp-server · 85 tokens

prompt-check

Live-test every MCP Prompt in src/prompts.ts through the real MCP protocol (not a static read) across every argument combination. Use when a prompt is added or its argument-handling logic changes, or as part of a live-audit pass.

Grinv/anilist-mcp-server · 53 tokens

tool-description-check

Self-check a new or edited MCP tool description/field .describe() text before committing — verify every behavioral claim against live testing, check for contradictions with sibling tools, and score against Glama's Tool Definition Quality Score (TDQS) rubric. Use whenever a tool description or schema field description…

Grinv/anilist-mcp-server · 74 tokens

release

Cut a release of anilist-mcp-server — draft CHANGELOG entries, check docs/metadata consistency, then bump/tag/push. Use when asked to release, cut a version, or publish a new version of this package.

Grinv/anilist-mcp-server · 48 tokens

fixture-accuracy-check

Make sure a mocked-fetch test fixture mirrors AniList's real GraphQL response shape, not just whatever fields make the current code pass. Use before writing or changing a fixture in src/tests/.test.ts.

Grinv/anilist-mcp-server · 48 tokens

docs-consistency-check

Check README/manifest.json/server.json/CHANGELOG.md/AGENTS.md and docs/.md for drift against the actual registered tools and source. Use after adding, renaming, or removing a tool, or as part of a live-audit pass.

Grinv/anilist-mcp-server · 56 tokens