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 commands/danielmiessler/paiplugin/capture-learninggit clone --depth 1 https://github.com/danielmiessler/PAIPluginWhat 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 | $0.00000 | $0.00660 |
| Opus 5 | $0.00000 | $0.00330 |
| Sonnet 5 | $0.00000 | $0.00132 |
| Haiku 4.5 | $0.00000 | $0.00066 |
Grade A, and why
capture-learning 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 2d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
capture-learning Command
Capture comprehensive problem-solving narratives from our work sessions, documenting not just the solution but the entire journey of discovery.
Purpose
This command captures the full narrative of problem-solving: what we thought was true, what we discovered was actually true, the troubleshooting journey, and the lessons learned. This narrative format makes it easy to harvest insights for updating documentation, commands, or pipelines.
Usage
# Interactive mode - guides you through the narrative
bun ${PAI_DIR}/commands/capture-learning.ts
# Direct mode with full narrative (all 6 arguments)
bun ${PAI_DIR}/commands/capture-learning.ts "problem" "initial assumption" "actual reality" "troubleshooting steps" "solution" "key takeaway"
Trigger Phrases
When you say any of these, I'll capture our learning:
- "Great job, log this"
- "Nice work, make a record"
- "Document this"
- "Capture this learning"
- "Save this for later"
- "That worked!"
The Narrative Structure
The command captures a complete story with these elements:
- The Problem - What issue did we encounter?
- Initial Assumption - "We thought this was true..."
- Actual Reality - "What we realized was actually true..."
- Troubleshooting Journey - Steps we took to discover the truth
- The Solution - What finally worked
- The Takeaway - "So now we know..." or "So now we do it this way..."
Why This Format?
This narrative approach helps us:
- Remember the journey, not just the destination
- Understand WHY the solution works
- Recognize similar patterns in future problems
- Update our mental models and documentation
- Share knowledge effectively with others
Output
Files are saved to: ${PAI_DIR}/context/learnings/
Named with format: YYYY-MM-DD-problem-description.md
Each file contains:
- Full narrative story
- Before/after comparison
- Technical details and commands used
- Actionable takeaways for future reference
Example Output
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.
- 2d ago First seen · 101 lines · 0 tokens per session scan A 7e029c9a3b36
capture-learning is a command published in the GitHub repository danielmiessler/PAIPlugin (56 stars, last pushed 9mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 660 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 2026-08-30.
Other commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
component
Scaffold a new React component grounded in the paper-mono primitives. Requires explicit kind or a nearest-existing-component match. No empty divs, no speculative scaffolding.
memory-store
Store an insight, decision, or pattern to memory.
review
Cold re-quiz on code that already shipped — your own session commits, not the change in front of you.
no-vibe
Enter no-vibe mode in OpenCode (tutor mode, no direct project file writes).
teach-me-testing
Teach testing progressively through structured sessions. Use when user says ""lets learn testing"" or ""I want to study test practices"".