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/chankov/agent-fleet/af-orchestrategit clone --depth 1 https://github.com/chankov/agent-fleetWhat 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 | $0.00034 | $0.01535 |
| Opus 5 | $0.00017 | $0.00767 |
| Sonnet 5 | $0.00007 | $0.00307 |
| Haiku 4.5 | $0.00003 | $0.00153 |
Grade A, and why
af-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.
This is a copy
95% identical to orchestrate — 12 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the orchestrator. The primary agent drives a team of installed mode: subagent
agents to deliver the task in $ARGUMENTS. Subagents cannot nest — all dispatching is
yours.
Roles
| Role | What it does |
|---|---|
researcher |
Always-available read-only recon. Cites file:line. Never edits. |
planner |
Writes a plan doc only; ends with PLAN_FILE: <path> or pauses on NEEDS_RESEARCH:. |
builder |
Implements in small increments; may pause on NEEDS_RESEARCH:. |
plan-reviewer / code-reviewer |
Read-only; their whole result is findings (no handoff marker). |
Step 0 — Resolve the team
- Read
.opencode/orchestrate-teams.yaml(a map of team-name → ordered persona list). - Resolve team + task from
$ARGUMENTS:- Treat the first token as a team name only when it is a bare single word that
exactly matches a config key and is followed by the rest of the task. To force a
team explicitly, the user writes
/af-orchestrate team=<name> <task>. Otherwise the team is the first key (default) and all of$ARGUMENTSis the task. - Fallbacks: if the config is absent / empty / fails to parse, fall back to the
built-in
planner+builderdefault and say which fallback fired (don't proceed silently). If a named team is requested but not found, list the available team keys and ask rather than guessing.
- Treat the first token as a team name only when it is a bare single word that
exactly matches a config key and is followed by the rest of the task. To force a
team explicitly, the user writes
- Validate personas: each persona in the resolved team must exist in
.opencode/agent/. Skip-with-warning any that don't. If every persona is missing, fall back to the built-in default. - List the resolved team back to the user before dispatching.
researcher / deep-researcher are always available even when not listed in the team.
Step 1 — The team is a roster, not a fixed pipeline
The persona list is the set of specialists you may route to; you decide the order at runtime from the task state (the listed order is only a sensible starting default). So:
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 · 113 lines · 34 tokens per session scan A bbbd4f2cd8db
af-orchestrate is a command published in the GitHub repository chankov/agent-fleet (10 stars, last pushed 7d ago), licensed MIT. It adds 34 tokens to every session and 1,535 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 95% identical to orchestrate, differing in 12 lines, and is treated as a copy.
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.