Borrowing it
Nothing to install: this file belongs to Kulaxyz/self-learning-skills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Kulaxyz/self-learning-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/Kulaxyz/self-learning-skillsWrote 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.
[](https://agentmods.dev/instructions/kulaxyz/self-learning-skills/agents-md)<a href="https://agentmods.dev/instructions/kulaxyz/self-learning-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/kulaxyz/self-learning-skills/agents-md/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.
<a href="https://agentmods.dev/instructions/kulaxyz/self-learning-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/kulaxyz/self-learning-skills/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00846 | $0.00846 |
| Opus 5.5 | $0.00338 | $0.00338 |
| Sonnet 5.5 | $0.00169 | $0.00169 |
| Haiku 4.5 | $0.00085 | $0.00085 |
Grade A, and why
self-learning-skills AGENTS.md 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Self-learning (for AI coding agents)
This file makes any coding agent self-improving: recognize a hard-won "golden path" during a task and persist it so the next session starts already knowing it, instead of rediscovering how to reach the DB, where the creds live, how to deploy, or how to verify a change live.
It works with any agent that reads a standing instructions file (Codex, Zed,
Aider, Gemini CLI, …). Richer, tool-native installs exist too — a Claude Code
skill (skills/self-learning/SKILL.md) and a Cursor rule
(.cursor/rules/self-learning.mdc); see the README. This file is the portable,
lowest-common-denominator version.
The loop
1. Recognize the moment. Any one of these is a cue:
- a task only worked after several attempts, wrong turns, or a correction;
- you discovered project facts you didn't know up front — where creds/env vars live, a non-obvious command, a required sequence, a gotcha;
- an operational workflow likely to recur (reach the dev/prod DB, deploy, run migrations, seed data, verify live, tail the right logs);
- the user says "remember this" / "don't make me re-explain this next time".
Act on the cue immediately — don't ask permission first. Capture it, then tell the user what you saved and where. They can always edit or delete it.
2. Capture it where your tool auto-loads knowledge next session:
- Claude Code / any Agent Skills client → a new
skills/<name>/SKILL.md - Cursor → a new
.cursor/rules/learned/<name>.mdc - Otherwise → append a dated entry under Learned below, or to your project's notes/memory file.
Capture the procedure (commands, paths, the required order, gotchas) — not a one-off answer — and the failures too: the approaches you ruled out and why, so next time skips the dead-ends.
3. Reuse. Next session the persisted entry loads automatically (by skill/rule description, or because this file is always read) and you start from the golden path.
Promotion rule
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.
- 1mo ago First seen · 73 lines · 846 tokens per session scan A a5be9046eff4
self-learning-skills AGENTS.md is an instructions file published in the GitHub repository Kulaxyz/self-learning-skills (971 stars, last pushed 1mo ago), licensed MIT. It adds 846 tokens to every session, about $0.0034 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.