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/s3rgiosan/agent-smith/orchestrategit clone --depth 1 https://github.com/s3rgiosan/agent-smithWrote 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/s3rgiosan/agent-smith/orchestrate)<a href="https://agentmods.dev/commands/s3rgiosan/agent-smith/orchestrate"><img src="https://agentmods.dev/badge/commands/s3rgiosan/agent-smith/orchestrate.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 | $0.00021 | $0.01365 |
| Opus 5 | $0.00010 | $0.00682 |
| Sonnet 5 | $0.00004 | $0.00273 |
| Haiku 4.5 | $0.00002 | $0.00136 |
Grade A, and why
orchestrate 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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrator mode
This turn runs on Fable. Fable time is the scarce resource here, so it buys three things and nothing else:
- Judgment about what to do — reading the request, choosing an approach, splitting it into pieces, spotting what could go wrong
- Handing pieces out — writing briefs a fresh subagent can act on, and deciding what runs now versus after something else
- Judgment about what came back — checking the work against the brief, integrating it, catching the gaps
Any keystroke of actual work belongs to a cheaper model. Dispatch it with the Agent tool and a model override.
The task
$ARGUMENTS
If no task text was substituted above, ask what to orchestrate. Do not pick something plausible and start.
About the model switch
model: fable in this file lasts until the end of this turn. The next prompt goes back to whatever the session was set to.
- Session already on Fable → nothing to say.
- Session on something else and the job needs more than one turn → say once that
/orchestrateshould be re-invoked on the turns that are actually planning or verification turns, and left alone on the rest. Do not suggest/model fableas the default; a session pinned to Fable pays Fable rates for every turn, including the ones that only relay a subagent result.
Never state or imply that the session model itself changed. It did not.
One edge: a session running an extended-context variant (e.g. fable[1m]) drops to the plain fable context window for this turn, because the override wins. Only relevant when the conversation is already enormous; if that bites, /model fable[1m] and skip re-invoking this command.
Who gets what
| The work | Where it goes |
|---|---|
| Deciding the approach, breaking the task apart | Fable, right here |
| Checking returned work, integrating it, the final call | Fable, right here |
| Finding things in the codebase, "where does X live", "how does Y work" | Explore, sonnet |
| Building something the brief already specifies precisely | general-purpose, sonnet |
| Work where the shape isn't settled, or a bug that resists the obvious fix | general-purpose, opus |
| Renames, repetitive edits, scaffolding, formatting, boilerplate | haiku — most edit volume is mechanical, so this is the default for it |
| Tests against a spec that already exists | sonnet |
| Running the build, tests, or linter | general-purpose, haiku — it returns pass/fail plus the failing lines, so raw output never lands in this turn |
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 · 73 lines · 21 tokens per session scan A 62e5100c7dbe
orchestrate is a command published in the GitHub repository s3rgiosan/agent-smith (2 stars, last pushed 27d ago), licensed MIT. It adds 21 tokens to every session and 1,365 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.