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/musingfox/cc-plugins/omtgit clone --depth 1 https://github.com/musingfox/cc-pluginsWhat 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 | $0.00031 | $0.04727 |
| Opus 5 | $0.00015 | $0.02364 |
| Sonnet 5 | $0.00006 | $0.00945 |
| Haiku 4.5 | $0.00003 | $0.00473 |
Grade C, and why
omt scanned grade C with 1 finding 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf .agents/outputs/ How it starts
The opening of the file, as written. The whole thing — 572 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/omt — OMT Orchestrator
Full lifecycle orchestrator for the OMT Agent-First workflow. Dispatches all agents, presents the consensus gate, and runs the execution loop. The human provides a goal and approves consensus — everything else is autonomous.
/omt "Build feature X"
→ Step 1-3: Capture goal, validate workspace, check resume
→ Step 4: Initialize state
→ Step 5: Dispatch @pm (autonomous requirements)
→ Step 6: Dispatch @arch (autonomous architecture)
→ Step 7: Dispatch @hive (consensus analysis) → present to user → approve
→ Step 8: Execute @dev → @reviewer loop per stage
→ Step 9: Completion report
Instructions
Step 1: Capture Goal
The user's argument is the goal description. Store it as $GOAL.
If no argument is provided, ask the user:
What do you want to build? Describe the goal in detail.
Example: "Implement JWT-based authentication with refresh token rotation and role-based access control"
Validate that the goal is at least 10 characters. If too brief, ask for more detail.
Step 2: Validate Workspace
Check if .agents/ directory exists:
ls .agents/
If .agents/ does not exist:
Agent workspace not initialized.
Run /init-agents first to set up the workspace, then run /omt again.
Stop execution here if workspace is missing.
VCS Detection
Detect the VCS environment (one-time check):
jj root 2>/dev/null && echo "USE_JJ=true" || echo "USE_JJ=false"
Store the result as $USE_JJ for use throughout the session. This determines how milestone commits are created.
Step 2.5: Resume Detection
Check for existing output files to detect an interrupted session:
Resume detection:
1. Read .agents/goal.md for the original goal
2. Check output file existence:
- .agents/outputs/pm.md → PM completed
- .agents/outputs/arch.md → Arch completed
- .agents/outputs/hive-consensus.md → Consensus analysis done
- .agents/outputs/dev/stage-*.md → count completed dev stages
- .agents/outputs/reviews/stage-*.md → count completed review stages
3. Determine re-entry point from file existence
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 · 572 lines · 31 tokens per session scan C 83248df7ec22
omt is a command published in the GitHub repository musingfox/cc-plugins (2 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 4,727 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.