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/jonase47/ccpr/learninggit clone --depth 1 https://github.com/jonase47/ccprWhat 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 | $0.00110 |
| Opus 5 | $0.00000 | $0.00055 |
| Sonnet 5 | $0.00000 | $0.00022 |
| Haiku 4.5 | $0.00000 | $0.00011 |
Grade A, and why
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 yesterday.
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.
What it actually says
Continuous Learning (2 commands)
Meta-commands for capturing session insight back into the system.
| Command | Title | Description |
|---|---|---|
/instinct |
Instinct Management | Manage instincts (confidence-based rules from session experience). |
/postmortem |
Session Postmortem | Analyze the last session and extract instinct proposals. |
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.
- yesterday First seen · 16 lines · 0 tokens per session scan A 5b5b2aed785b
learning is a command published in the GitHub repository jonase47/ccpr (1 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 110 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 2026-08-31.
Other commands, from other repositories
research
Research a topic from the web and build teaching-quality notes with real sources.
polish
Improve existing notes in place — clearer structure, bullet-first, artifacts that teach, better links.
reflect
Reflect on recent work — log lessons to the journal and propose distilled rule updates for review.
kb-ingest
Esegui un ingest nella LLM Wiki per il progetto o argomento specificato: $ARGUMENTS.
kb-lint
Esegui un controllo qualità completo della LLM Wiki in $LLMWIKIPATH.
repo-to-course
Turn a codebase into a structured tutorial course — markdown, GitHub Pages site, or interactive HTML.