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/ackeskin/contexture/orchestrategit clone --depth 1 https://github.com/AcKeskin/contextureWhat 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 | $0.00052 | $0.00439 |
| Opus 5 | $0.00026 | $0.00219 |
| Sonnet 5 | $0.00010 | $0.00088 |
| Haiku 4.5 | $0.00005 | $0.00044 |
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 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.
What it actually says
Run the orchestrate skill.
Forms:
/orchestrate— decompose the current goal into units and run the four-question convergence protocol over them.
Examples:
/orchestrate— "split this across agents and converge the results."- Natural language: "fan this goal out", "set up worktrees for these branches", "split this across agents and bring it back together."
The skill owns the convergence discipline for goal-directed concurrency (one objective decomposed into interdependent parts that reconverge), not the failure-directed fan-out dispatch already covers. Four questions: Q1 decompose (partition into units + dependency graph; refuse to fan out a single sequential chain), Q2 place (per unit: shared tree / worktree-each / serialize, under the hard invariant that two concurrent units writing the same files never share a working tree), Q3 dispatch (delegates to dispatch unchanged — the subagent recursion caps fire on every unit), Q3.5 keep-on-track (prevent-at-dispatch only — there is no mid-flight window into a running subagent; hard placement is the real scope fence, prompt fences are supplementary), Q4 converge (verify-then-combine: boundary audit + separate-verifier pass then synthesis; never trust a unit's self-reported success).
It is a caller of using-git-worktrees (isolation) and dispatch (the fan-out engine); it never re-implements worktree setup or dispatch mechanics.
Does not auto-fire. Not for independent-failure fan-out (that's dispatch directly), not single-worktree isolation (that's using-git-worktrees directly).
See ~/.claude/skills/orchestrate/SKILL.md for the full procedure.
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 · 23 lines · 52 tokens per session scan A 82bd518a9b44
orchestrate is a command published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 52 tokens to every session and 439 once invoked, about $0.0003 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
address
Address code review feedback — corroborate, validate, and implement changes from a review's final.md.
sync-reviewers
Sync reviewer metadata from markdown files to reviewers-meta.json for the dashboard.
translate-review-to-single-human
Translate a multi-reviewer code review into a single human-voice GitHub PR comment.
map
Generate a Code Review Map to help navigate large, complex changesets.
post
Post the current OCR review to a GitHub PR.
review
Run an AI-powered multi-agent code review on your changes.