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/divyamrastogi/model-orchestration/delegategit clone --depth 1 https://github.com/divyamrastogi/model-orchestrationWhat 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 | $0.00016 | $0.00302 |
| Opus 5 | $0.00008 | $0.00151 |
| Sonnet 5 | $0.00003 | $0.00060 |
| Haiku 4.5 | $0.00002 | $0.00030 |
Grade A, and why
delegate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Delegate a task to a model worker per the orchestrating-model-workers skill (read its SKILL.md in this plugin if you haven't this session).
Arguments given: "$ARGUMENTS"
- Pick the worker: if the first argument names one (check
"${CLAUDE_PLUGIN_ROOT}/scripts/setup-worker.sh" list), use it; otherwise use the only configured worker, or ask which. - Write a complete, self-contained spec for the task: relevant file paths, acceptance criteria, constraints, and the instruction to return a short summary with pointers (never full file dumps).
- Dispatch headlessly:
~/.claude-workers/<name>/run -p "<spec>" --permission-mode acceptEdits(drop--permission-modefor read-only research tasks). - Revision gate — audit the result against the acceptance criteria yourself: read the diff, run the tests or the code. Do not present unverified worker output as done.
- If it misses: send the SAME worker back out with specific revision notes. After a second miss, do the task yourself or via a smarter subagent — judge the output, not the price tag.
- Report to the user: what was delegated, audit verdict, and the final result.
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.
- 3d ago First seen · 26 lines · 16 tokens per session scan A 6e153c455cca
delegate is a command published in the GitHub repository divyamrastogi/model-orchestration (4 stars, last pushed 3d ago), licensed MIT. It adds 16 tokens to every session and 302 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
git
Git operations with intelligent commit messages and workflow optimization.
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.