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.
npx agentmods add instructions/melodykoh/learning-loop-skill/claude-mdgit clone --depth 1 https://github.com/melodykoh/learning-loop-skillWhat 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 | $0.01199 | $0.01199 |
| Opus 5 | $0.00600 | $0.00600 |
| Sonnet 5 | $0.00240 | $0.00240 |
| Haiku 4.5 | $0.00120 | $0.00120 |
Grade A, and why
learning-loop-skill CLAUDE.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 3d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learning-Loop Skill: Development Conventions
For Claude: Follow these conventions when modifying this skill.
Mandatory: Update SESSION_LOG.md
Every time you modify SKILL.md, you MUST also update SESSION_LOG.md.
What to Document
- What problem you were solving — Why was this change needed?
- What you investigated — What approaches did you consider or try?
- What you discovered — Any non-obvious findings, especially failures
- What you decided — The choice made and its rationale
- What changed — Summary of files/sections modified
SESSION_LOG Entry Template
## Session: [Date] — [Brief Title]
### Context
[Why this session happened, what triggered it]
### Problem
[What wasn't working or what needed to change]
### Investigation (if applicable)
[What approaches were tried, what was discovered]
### Decision
[What was decided and why]
### Changes Made
| File | Change |
|------|--------|
| SKILL.md | [What changed] |
| ... | ... |
Why This Matters
Git commits show what changed. SESSION_LOG shows why.
Without SESSION_LOG, future sessions might:
- Re-investigate already-settled questions
- Revert intentional design decisions
- Lose context about failed approaches
Mandatory: Commit and Push
After updating both SKILL.md and SESSION_LOG.md:
-
Stage both files:
git add SKILL.md SESSION_LOG.md -
Commit with descriptive message:
git commit -m "Brief description of change [Optional: Key decision or finding] Co-Authored-By: Claude Opus 4.6 <[email protected]>" -
Push to origin:
git push
File Purposes
| File | Purpose | When to Update |
|---|---|---|
SKILL.md |
The skill logic itself | When behavior changes |
SESSION_LOG.md |
Reasoning trail | Every time SKILL.md changes |
README.md |
User-facing docs | When usage/installation changes |
CLAUDE.md |
Development conventions | Rarely (this file) |
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.
- 3d ago First seen · 135 lines · 1,199 tokens per session scan A b961758e0780
learning-loop-skill CLAUDE.md is an instructions file published in the GitHub repository melodykoh/learning-loop-skill (20 stars, last pushed 5d ago), licensed MIT. It adds 1,199 tokens to every session, about $0.0060 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 2026-08-30.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.