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/plan-activategit clone --depth 1 https://github.com/MilindGaharwar/fettleWhat 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 | $0.00014 | $0.00580 |
| Opus 5 | $0.00007 | $0.00290 |
| Sonnet 5 | $0.00003 | $0.00116 |
| Haiku 4.5 | $0.00001 | $0.00058 |
Grade A, and why
plan-activate 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
98% identical to fettle-plan-activate — 4 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.
How it starts
The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fettle:plan-activate
Activate a development plan to unlock implementation file edits.
Steps
-
Ask the user which plan file to activate. If they provide a path, use it. If not, search for
.mdfiles indocs/plans/and present the list. -
Read the plan file completely.
-
Run the structural validator:
python3 -m fettle.plan_validator <PLAN_PATH>If it fails, report every error verbatim and do NOT activate. The errors name the exact WP and missing method type. Fix the plan first.
-
Check for adversarial review:
- Look for a
## Council Reviewor## Adversarial Reviewsection in the plan, OR - Check if a council report file is referenced in the plan header (e.g.,
council_report: /path/to/report.md) - If neither exists: WARN the user that no adversarial review is on record. For plans with implementation tasks, recommend an adversarial review pass (a second model or a colleague red-teaming the plan) before activation. Strongly recommended but does not hard-block.
- Look for a
-
If validation passes, write the marker file:
echo '{"plan": "<PLAN_PATH>", "approved": true, "ts": <UNIX_TIMESTAMP>}' > .fettle/state/active-plan.json -
Confirm activation:
Plan activated: <plan name> Path: <plan path> Work packages: <count> Implementation file edits are now allowed.
Validation rules enforced (plan_validator.py)
Every WP containing at least one implementation method task (TDD, BUILD, FIX, REFACTOR, CODE, INTEGRATION) must also contain:
| Required method | What it checks |
|---|---|
| TDD | Unit tests written before implementation |
| INTEGRATION | End-to-end test against the running system |
| REGRESSION | Named failure scenario (must cite incident/bug -- generic "regression test" is blocked) |
| LIVE | Exact command + observable outcome (must include an actual command -- "verify it works" is blocked) |
WPs containing only INSPECT, VERIFY, REVIEW, or PROPERTY tasks are exempt.
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 · 62 lines · 14 tokens per session scan A 43419f5fa5e4
plan-activate is a command published in the GitHub repository MilindGaharwar/fettle (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 14 tokens to every session and 580 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to fettle-plan-activate, differing in 4 lines, and is treated as a copy.
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.
aod.blueprint
Unified project setup & story generation — auto-detects new vs existing projects.
maintainer
Meta-skill that loads all llmwiki governance docs and exposes the three maintainer slash commands.
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.
setup_research_plan
Set up or start a research project.