Borrowing it
Nothing to install: this file belongs to anthony-spruyt/claude-plugins. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/anthony-spruyt/claude-plugins/main/.claude/skills/orchestration/SKILL.mdgit clone --depth 1 https://github.com/anthony-spruyt/claude-pluginsWrote 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/anthony-spruyt/claude-plugins/orchestration)<a href="https://agentmods.dev/skills/anthony-spruyt/claude-plugins/orchestration"><img src="https://agentmods.dev/badge/skills/anthony-spruyt/claude-plugins/orchestration/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/anthony-spruyt/claude-plugins/orchestration"><img src="https://agentmods.dev/badge/skills/anthony-spruyt/claude-plugins/orchestration.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00065 | $0.01856 |
| Opus 5.5 | $0.00026 | $0.00742 |
| Sonnet 5.5 | $0.00013 | $0.00371 |
| Haiku 4.5 | $0.00006 | $0.00186 |
Grade A, and why
orchestration 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestration
Routing
The main session plans, decides and talks to the owner. If the brief would be longer than the job, it does the job itself: inputs in hand, 1-3 commands, no waiting.
| Work | Helper (model) |
|---|---|
| Edits, commits, fix rounds, rework | builder (sonnet) |
| Waiting or polling, noisy logs, batch sweeps | chore-runner (haiku), in background |
| Reviews, fix-checks, attacker-minded reviews | reviewer (opus) |
| Deep investigation | general-purpose (opus) |
| Broad read-only search across files or repos | Explore (haiku) |
Push reviewed commits yourself from the builder's workspace.sh clone, never the shared checkout, with push-reviewed.sh <base> <sha> <branch>, only once fresh reviews cover that exact range and the last round is READY (every full-review lens, then each fix-check); if it stops, tell the owner. Give the range it prints to the CI wait and any post-push validator the repo's rules name.
Interview, then design, before delegating
New work, or a change to an approach the owner picked, starts with the interview skill, even when an issue already describes it: an issue records the ask, not the owner's current intent. Then show the owner a design: current setup (check existing controls first), target layout, per-repo changes, migration order, and the riskiest assumption with how a helper will prove it. Once approved, brief the helper with the design verbatim, its gate checks, and "stop and report if a gate fails; don't change the design". Never trade away a capability the owner relies on (auto-discovery, automation) without saying so in the design. Write the design of large or risky work to a file and run spec-review on it before showing the owner: a design flaw found in code review costs fix rounds. Fix rounds need no new interview or design. Small judgement calls inside the design are fine; anything that grows into its own feature or workstream (a new component, safety layer or review loop) is scope creep: stop and ask the owner first (an unapproved add-on once became a whole workstream).
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 · 71 lines · 65 tokens per session scan A 313a5bb9d193
orchestration is a skill published in the GitHub repository anthony-spruyt/claude-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 65 tokens to every session and 1,856 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-10-16.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…