claude-init: Command for Claude Code

.github/prompts/self-learn.md

self-learn is a command for Claude Code, GitHub Copilot from yash-gadodia/claude-init. It costs 0 tokens per session (627 once invoked), scanned A, original, MIT.

A repeatable review process for studying changes in the Claude Code ecosystem and suggesting at most one improvement to claude-init. It requires checking project notes, official sources, and comparable repositories before making a proposal.

In plain words
What is it for?
It is for reviewing new Claude Code features, skills, documentation, and related projects, then deciding whether one concrete configuration improvement is justified.
Why use it?
It reduces speculative changes and prevents repeating ideas that were already rejected. It also gives each review a clear evidence and decision process.

Command for Claude CodeGitHub Copilot

Written for Claude Code and GitHub Copilot: shipped in a Claude Code plugin, but also a Copilot chat mode or prompt. Also seen: mentions subagents; mentions Claude Code.

This is yash-gadodia/claude-init's own configuration. It tells Claude Code and GitHub Copilot how to work on claude-init itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-init configures →

Part of the claude-init plugin — 11 skills, 1 command, 7 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to yash-gadodia/claude-init. 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/yash-gadodia/claude-init/main/.github/prompts/self-learn.md
Clone the repo
git clone --depth 1 https://github.com/yash-gadodia/claude-init

Made for: Claude Code, GitHub Copilot.

Or install claude-init, the plugin that ships this one along with the rest of its 11 skills, 1 command, 7 agents.

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 self-learn

README.md
[![agentmods](https://agentmods.dev/badge/commands/yash-gadodia/claude-init/self-learn.svg)](https://agentmods.dev/commands/yash-gadodia/claude-init/self-learn)
Your own site
<a href="https://agentmods.dev/commands/yash-gadodia/claude-init/self-learn"><img src="https://agentmods.dev/badge/commands/yash-gadodia/claude-init/self-learn.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 627 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 $0.00000 $0.00627
Opus 5 $0.00000 $0.00313
Sonnet 5 $0.00000 $0.00125
Haiku 4.5 $0.00000 $0.00063

Measured today against content hash c79e3ca8298f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

self-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 today.

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.

.github/prompts/self-learn.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Weekly Self-Learning Loop

Study the Claude Code ecosystem and propose AT MOST ONE concrete improvement to claude-init per run. Evidence over speculation. If nothing clears the bar this week, that is a valid outcome.

Phase 1: Gather

  1. Read LEARNINGS.md FIRST — the reject list and last-checked dates. Never re-propose anything marked rejected unless its revisit date has passed.
  2. Check upstream changes since the Last checked dates in LEARNINGS.md:
    • anthropics/claude-code CHANGELOG.md — new/changed Claude Code features
    • anthropics/skills — new official Agent Skills or format changes
    • Official docs at code.claude.com/docs (skills, hooks, sub-agents, plugins, memory pages)
  3. Scan comparable repos for new patterns (recent commits/README changes):
    • obra/superpowers — skill methodology
    • trailofbits/claude-code-config — security-first config
    • hesreallyhim/awesome-claude-code — new ecosystem entries worth studying
    • VoltAgent/awesome-agent-skills — cross-platform skill patterns

Phase 2: Analyze

For each candidate idea, require ALL of:

  • Makes claude-init's GENERATED configs better (not just interesting)
  • Fits in templates/, docs, or the four self-skills — no core rewrite
  • Has a citable source (URL to repo, changelog entry, or doc page)
  • Not in LEARNINGS.md as rejected (or revisit date has passed)

Pick the single strongest idea, or none.

Phase 3: Apply (commit directly to main)

If you have one improvement:

  1. Make the change on main — max ~200 changed lines, templates/docs/skills only
  2. Update LEARNINGS.md: add this cycle's entry (adopted idea + any rejected candidates with reasons), refresh all Last checked dates
  3. Run bash tests/run.sh — MUST pass before you commit. If it fails and you can't fix it within the diff budget, revert everything except the LEARNINGS.md entry (log the idea as "attempted, tests failed") and commit only that
  4. Commit to main with the source URLs in the message, prefixed [self-learn], and push

Read the full file on GitHub · 46 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. today First seen · 46 lines · 0 tokens per session scan A c79e3ca8298f

Subscribe to this mod's changes

self-learn is a command published in the GitHub repository yash-gadodia/claude-init (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 627 tokens. 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 2026-09-08.