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 skills add odysseus0/claude-orchestrate --skill orchestrategit clone --depth 1 https://github.com/odysseus0/claude-orchestrateWrote 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/skills/odysseus0/claude-orchestrate/orchestrate)<a href="https://agentmods.dev/skills/odysseus0/claude-orchestrate/orchestrate"><img src="https://agentmods.dev/badge/skills/odysseus0/claude-orchestrate/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 5.1 | $0.00054 | $0.01055 |
| Opus 5 | $0.00027 | $0.00528 |
| Sonnet 5 | $0.00011 | $0.00211 |
| Haiku 4.5 | $0.00005 | $0.00105 |
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 7d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrate
An explicit /orchestrate:orchestrate <goal> fans out a large task across parallel Claude Code subagents running in isolated git worktrees. Workers don't talk to each other; they talk up through structured handoffs. The spawn, wait, and handoff loop lives in the planner's own turn. The planner writes plan.json, drives the loop, reads handoffs to decide what comes next. Long-running agent loops drift; a script with a JSON state file keeps its footing — in Claude Code the "script" is the planner's structured procedure in references/planner.md.
Adapted from Cursor's /orchestrate skill (cursor/plugins/orchestrate). Substrate:
- No dispatcher. The Claude Code session is local; it IS the root planner.
- Uniform spawn substrate. Every spawn (worker, verifier, subplanner) is a fresh top-level Claude Code session in its own isolated git worktree, spawned via
claude --bg --worktree <name>and awaited via the bundledclaude-bg-waitwrapper (on PATH via<plugin>/bin/). Sessions are daemon-supervised, have stable ids visible inclaude agents --json, and can be re-bound to after parent crashes (recoverRunning equivalent). - No Slack. Andon (cross-tree pause) is file-based: the operator touches
.orchestrate/<rootSlug>/andonfrom any terminal to halt new spawns across the tree; removing the file resumes. Every planner (root + all subplanner descendants) checks the root's andon file before each spawn cycle. Seereferences/planner.mdPhase 2 sweep step 0. - No subprocess heartbeat; the planner's own turn drives the loop.
Core principles
These rules make the tree self-converging without global coordination.
- Planners own scopes and publish tasks. They do no coding. Writing
plan.json, reading handoffs, and deciding what's next are planner work. Editing files, runninggit merge, and fixing conflicts inline are not. If a planner feels the urge to code, it publishes a task for a worker instead. - Planners don't know who picks up their tasks. Routing each task to a fresh top-level Claude Code session (via
claude-bg-wait <worktree-name> <prompt>) is mechanical. The planner's mental model stays at the task level. - Workers are isolated. One task, one worktree, no channel to any other agent. One handoff when done.
- Subplanners are recursive planners. A planner publishes a "subplan this slice" task; the subplanner fully owns that slice and hands back an aggregated handoff. Subplanners can spawn their own subplanners — no depth limit.
- Continuous motion via handoffs. A planner that thought it was done can receive a late handoff and replan. No "finished" state until the planner decides to stop publishing.
- Propagation, not synchronization. No cross-talk between siblings. No shared state between levels. Each level sees only its children's handoffs.
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 46 lines · 54 tokens per session scan A fe384ce5b454
orchestrate is a skill published in the GitHub repository odysseus0/claude-orchestrate (1 stars, last pushed 3mo ago), licensed MIT. It adds 54 tokens to every session and 1,055 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
deploy-from-stale-worktree-silent-rollback
Diagnose "I deployed a new Cloud Run / Docker image but a bunch of recently merged fixes regressed in production." Use when: (1) the deploy script does gcloud builds submit ... "${SCRIPTDIR}" or docker build (build context = local filesystem, NOT a git ref), (2) the user has many git worktrees / multiple checkouts of…
prep-pr-close-keyword-auto-closes-issue
Diagnose and prevent the trap where a scaffolding/prep/planning/handoff PR (one that ships a paste-ready prompt, an ADR, an implementation plan, or any docs-only artefact describing FUTURE work) contains a close-keyword like closes #N / fixes #N / resolves #N in its TITLE or BODY, which GitHub auto-applies at merge…
cross-worktree-spec-handoff-via-checkout-paths
Pass a shared file between two parallel sessions in different worktrees or branches, without merging to main first — a design spec, docs, a handoff prompt, a mockup. git checkout -- stages it. Use when a session says "the file doesn't exist". Not co editing.
docs-branch-off-feature-branch-smuggles-code
Catch the bug class where a "docs follow-up" PR silently ships the parent feature's code under a docs(sN): title because the docs branch was created from the current working branch (a feature branch), not from origin/main. Use when: (1) you just opened a PR titled docs(...) or chore(...) after wrapping up a feature…
merged-pr-not-deployed-gate-label-missing
Diagnose "I merged my PR + CI is green but the live service still doesn't show my changes." Use when: (1) a code-bearing PR has been squash-merged into main with all required status checks passing, (2) the user reports the change is still missing from the deployed environment minutes-to-hours later, (3) the repo has a…
multi-agent-skill-silent-phase-compression
Diagnose and fix silent compression of MANDATORY phases in multi-agent orchestrator skills (review panels, debate workflows, multi-reviewer pipelines). Use when: (1) a skill spec lists 10+ phases including parallel reviewer dispatch but the actual run "compresses Phase 4 (reflection) / Phase 5 (debate) / Phase 7…