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/milindgaharwar/fettle/fettle-learngit clone --depth 1 https://github.com/MilindGaharwar/fettleWrote 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/milindgaharwar/fettle/fettle-learn)<a href="https://agentmods.dev/commands/milindgaharwar/fettle/fettle-learn"><img src="https://agentmods.dev/badge/commands/milindgaharwar/fettle/fettle-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 | $0.00010 | $0.00323 |
| Opus 5 | $0.00005 | $0.00161 |
| Sonnet 5 | $0.00002 | $0.00065 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
fettle-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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- learn — 95% identical, 5 lines differ
What it actually says
/fettle:learn
Generate a semgrep rule from an incident description.
Usage
When the user invokes /fettle:learn, ask for the incident details:
- What failed? (the bug or vulnerability)
- What code pattern caused it?
- What should it look like instead?
Then run:
fettle learn --incident "INCIDENT_TEXT" --auto-save
The drafted rule lands in the rules/proposed/ quarantine (status: proposed)
with:
- Semgrep pattern
- Citation (incident reference)
- Violating fixture (tests/fixtures/learned/)
- Clean fixture (tests/fixtures/learned/)
Proposals are NEVER loaded by gates. Promotion to rules/learned/ is an
explicit human step.
Verification
After generating, verify the rule works against its fixtures:
semgrep --config rules/proposed/<rule-id>.yml tests/fixtures/learned/<rule-id>_violation.py
Should match the violation fixture and NOT match the clean fixture.
Approval
Review the quarantined proposals and promote the good ones:
fettle rules list
fettle rules promote <rule-id>
Promotion moves the rule to rules/learned/ (status: learned), where it can
be loaded via .fettle.toml. fettle rules promote refuses proposals with
an empty pattern.
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.
- 4d ago First seen · 53 lines · 10 tokens per session scan A 7e294f2186b0
fettle-learn is a command published in the GitHub repository MilindGaharwar/fettle (2 stars, last pushed today), licensed Apache-2.0. It adds 10 tokens to every session and 323 once invoked, about $0.0001 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 commands, from other repositories
corporate-launcher
Build a secure, branded, organization-specific launcher around an AI coding CLI (Claude Code, Codex CLI, Gemini CLI, Cursor, or Cline) so the user can.
send
Send a message to a running agent session. Use this to correct or direct a live agent mid-stream without killing and respawning it.
kb-ingest
Ingest external material into Sources/ inside the bound project KB, then update registry, index, and daily note as needed.
aod.blueprint
Unified project setup & story generation — auto-detects new vs existing projects.
ox-session-pause
belongs in the ox CLI JSON output (guidance field), not here. Skills are agent-specific wrappers; ox serves all agents (Codex, etc.). --> Suspend the current session recording. Local cache continues to receive entries, but the upload at stop time will exclude the suspended range.
generate-role
Resolve a need to a domain-expert role (existing, new leaf, or new parent) and draft it via the AUTHORING.md pipeline, opening a PR.