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.
git clone --depth 1 https://github.com/kylepelham/DriftWrote 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/commands/kylepelham/drift/learn)<a href="https://agentmods.dev/commands/kylepelham/drift/learn"><img src="https://agentmods.dev/badge/commands/kylepelham/drift/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 | $0.00018 | $0.00344 |
| Opus 5 | $0.00009 | $0.00172 |
| Sonnet 5 | $0.00004 | $0.00069 |
| Haiku 4.5 | $0.00002 | $0.00034 |
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 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.
This is a copy
100% identical to learn — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Analyze this session and extract non-obvious learnings to add to AGENTS.md files.
AGENTS.md files can exist at any directory level, not just the project root. When an agent reads a file, any AGENTS.md in parent directories are automatically loaded into the context of the tool read. Place learnings as close to the relevant code as possible:
- Project-wide learnings → root AGENTS.md
- Package/module-specific → packages/foo/AGENTS.md
- Feature-specific → src/auth/AGENTS.md
What counts as a learning (non-obvious discoveries only):
- Hidden relationships between files or modules
- Execution paths that differ from how code appears
- Non-obvious configuration, env vars, or flags
- Debugging breakthroughs when error messages were misleading
- API/tool quirks and workarounds
- Build/test commands not in README
- Architectural decisions and constraints
- Files that must change together
What NOT to include:
- Obvious facts from documentation
- Standard language/framework behavior
- Things already in an AGENTS.md
- Verbose explanations
- Session-specific details
Process:
- Review session for discoveries, errors that took multiple attempts, unexpected connections
- Determine scope - what directory does each learning apply to?
- Read existing AGENTS.md files at relevant levels
- Create or update AGENTS.md at the appropriate level
- Keep entries to 1-3 lines per insight
After updating, summarize which AGENTS.md files were created/updated and how many learnings per file.
$ARGUMENTS
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 · 43 lines · 18 tokens per session scan A 891675a8519c
learn is a command published in the GitHub repository kylepelham/Drift (20 stars, last pushed yesterday), licensed MIT. It adds 18 tokens to every session and 344 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to learn, differing in 0 lines, and is treated as a copy.
Other commands, from other repositories
context-load
Carga de contexto al inicio de sesión. Lee estado del workspace, decisiones recientes, último session save y actividad Git para arrancar con el big picture.
context-defer
Sistema de carga diferida — cargar comandos/reglas solo cuando se necesitan (85% reducción de overhead).
context-optimize
Analizar patrones de uso de contexto y sugerir optimizaciones al context-map.
cache-invalidate
Invalidación selectiva de capas de caché con rollback seguro.
cache-warm
Pre-calentar caché con contexto probable basado en hora y rol.
context-age
Envejecimiento semántico del decision-log — comprime y archiva decisiones antiguas.