A self-improvement routine for coding agents that reviews completed work and records reusable lessons in AGENTS.md, a file containing project instructions. It includes a rule for saving a lesson after repeated corrections.

Use it after difficult tasks, repeated corrections, or when a new project convention is discovered. It helps identify friction, turn it into a rule, and verify that the rule was saved.

It reduces the chance of repeating the same mistake across tasks or agent sessions. The written rules give the wider agent team a shared record of useful discoveries and preferences.

How OthmanAdi/APEX configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to OthmanAdi/APEX. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/OthmanAdi/APEX/main/.agents/skills/apex-learn/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/OthmanAdi/APEX

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/othmanadi/apex/apex-learn/github.svg)](https://agentmods.dev/skills/othmanadi/apex/apex-learn)

Your own site

<a href="https://agentmods.dev/skills/othmanadi/apex/apex-learn"><img src="https://agentmods.dev/badge/skills/othmanadi/apex/apex-learn/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/othmanadi/apex/apex-learn"><img src="https://agentmods.dev/badge/skills/othmanadi/apex/apex-learn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,012 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.

Model	Per session	Once invoked
Fable 5.1	$0.00079	$0.01012
Opus 5.5	$0.00032	$0.00405
Sonnet 5.5	$0.00016	$0.00202
Haiku 4.5	$0.00008	$0.00101

Measured 2mo ago against content hash 837e8a4e1267, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

apex-learn 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 2mo ago.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/append-learning.ps1, scripts/append-learning.sh), 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.

.agents/skills/apex-learn/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

APEX Learn

Analyze what happened during a task, extract reusable knowledge, and persist it to AGENTS.md so the entire agent team improves over time.

When to Use

Run this skill in any of these situations:

After completing a Tier 1, 2, or 3 task
When the human corrected you on the same issue twice (two-strike rule)
When you discovered a non-obvious pattern or convention
When a task took significantly longer than expected
When the human explicitly asks to update the rules

The Two-Strike Rule

This is the core mechanism. If you are corrected on the same type of issue twice:

First correction — Fix the issue, note it mentally
Second correction — Fix the issue AND run apex-learn to add a permanent rule

This prevents the same mistake from recurring across sessions.

Workflow

Identify friction points
Classify the learning
Draft the rule
Append to AGENTS.md
Verify the update

Step 1: Identify Friction Points

Ask yourself these questions about the completed task:

## Friction Analysis

1. Where did I get stuck or make mistakes?
2. What did the human correct me on?
3. What took longer than expected and why?
4. What assumptions did I make that were wrong?
5. What patterns did I discover that aren't documented?

Step 2: Classify the Learning

Each learning falls into one of these categories:

Category	Example	Where it Goes in AGENTS.md
Code style	"Always use named exports"	`## Code Style` section
Architecture	"Services never call controllers"	`## Architecture Rules` section
Workflow	"Always run tests before committing"	`## Workflow` section
Boundaries	"Never modify the auth module"	`## Boundaries` section
Preferences	"Prefer descriptive over short names"	`## Preferences` section
Tool usage	"Use pnpm, not npm"	`## Tools` section

Step 3: Draft the Rule

Write the rule in imperative form. Be specific and actionable:

Read the full file on GitHub · 134 lines

Files

What ships with it

3 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.

2mo ago First seen · 134 lines · 79 tokens per session scan A 837e8a4e1267

Subscribe to this mod's changes

apex-learn is a skill published in the GitHub repository OthmanAdi/APEX (2 stars, last pushed 7mo ago), licensed MIT. It adds 79 tokens to every session and 1,012 once invoked, about $0.0003 per session on Opus 5.5. 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 agents

apex-learn next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
apex-learnOthmanAdi/APEX	Skill	2	7mo ago	MIT	A	79	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex

APEX: Skill for Claude Code