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 skills add WhatIfWeDigDeeper/agent-skills --skill learngit clone --depth 1 https://github.com/WhatIfWeDigDeeper/agent-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/skills/whatifwedigdeeper/agent-skills/learn)<a href="https://agentmods.dev/skills/whatifwedigdeeper/agent-skills/learn"><img src="https://agentmods.dev/badge/skills/whatifwedigdeeper/agent-skills/learn.svg" alt="Measured on agentmods" 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 | $0.00150 | $0.02946 |
| Opus 5 | $0.00075 | $0.01473 |
| Sonnet 5 | $0.00030 | $0.00589 |
| Haiku 4.5 | $0.00015 | $0.00295 |
Grade A, and why
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 8d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Learn from Conversation
Analyze the conversation to extract lessons learned, then persist them to AI assistant configuration files or new skills.
Arguments
Optional text to narrow what to learn (e.g. sandbox workaround, that build fix).
If $ARGUMENTS is help, --help, -h, or ?, skip the workflow and read references/options.md.
If $ARGUMENTS is a non-empty, non-help string, use it as a focus filter in Step 2: only surface learnings related to the specified topic, skip unrelated findings.
Process
1. Detect Configurations and Existing Skills
for f in CLAUDE.md GEMINI.md AGENTS.md .cursorrules .github/copilot-instructions.md \
.windsurf/rules/rules.md .continuerc.json; do
[ -f "$f" ] && wc -l "$f"
done
find .cursor/rules -name "*.mdc" -exec wc -l {} \; 2>/dev/null
find . -name "SKILL.md" -type f 2>/dev/null | grep -v node_modules | \
xargs grep -l "^name:" | while read -r f; do grep -m1 "^name:" "$f" | sed 's/name: //'; done
Config detection:
- Single config found → use it
- Multiple configs found → MANDATORY: read
references/multiconfig-routing.mdin full to evaluate auto-skip vs. prompt before proceeding. - No configs found → MANDATORY: read
references/assistant-configs.mdin full to show init commands, then exit. Do NOT loadrefactoring.md,options.md, ormulticonfig-routing.mdat this step.
Size thresholds for any config file:
- < 400 lines: healthy, add directly
- 400–500 lines: add carefully, note the file is getting large
-
500 lines: MANDATORY: read
references/refactoring.mdin full before proceeding, then offer to refactor. Do NOT loadassistant-configs.mdfor this path unless also applying Route A changes.
2. Analyze Conversation
Default is reject. Each candidate learning must earn inclusion by passing three filters in order:
- Would I forget this? If any developer already knows it (
npm installbeforenpm start, commit before switching branches, read errors carefully), skip it. Baseline knowledge dilutes the config and trains agents to skim. - Is this already covered? Search existing config entries for the topic — if found, tightening the wording beats adding a second rule.
- Is this universal or local? Environment-specific workarounds (broken keyring, one repo's tooling quirk) must carry a scope qualifier, not be globalized.
What ships with it
6 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.
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.
- 8d ago First seen · 171 lines · 150 tokens per session scan A 58b05bba4252
learn is a skill published in the GitHub repository WhatIfWeDigDeeper/agent-skills (2 stars, last pushed 15d ago), licensed MIT. It adds 150 tokens to every session and 2,946 once invoked, about $0.0007 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 2026-08-31.
Other skills, from other repositories
learn-from-fix
Capture Elixir/Ecto/LiveView lessons and Hex API rules. Use after corrections or when asked to document learning, record a lesson, prevent a fixed mistake, or remember package guidance with --library.
skill-status
A study-progress companion that reads a saved JSON file to remember your learning plan, progress, predictions, and past notes between sessions.
cm-notebooklm
Sync high-value dev knowledge (skills, decisions, lessons) into Google NotebookLM for cloud recall, podcasts, and flashcards. Pairs with Dockit/deep-search. Use for NotebookLM, nlm, knowledge base, skill sync, or cross-machine AI memory.
peec-learn
Cross-project pattern layer for the Peec AI growth loop. After any Peec skill completes (or after peec-report closes a cycle), extract 1–3 concrete patterns from the output and persist them to SkillMind via mcpskillmindaddpattern / remember. On the next orchestrator run, recall matching patterns and pass them in as…
knowledge-content-routing
Two niche knowledge specialists not covered by existing document-format / documentation skills — Zettelkasten knowledge graph stewardship and enterprise training curriculum design. Use when the user wants to build a Luhmann-style atomic-note knowledge base with connectivity validation, or design a multi-track…
baoyu-comic
A tool for creating original educational comics that explain knowledge or ideas through multiple illustrated panels. It supports different art styles and tones and can create several comics in one batch.