Borrowing it
Nothing to install: this file belongs to luckeyfaraday/frontier-orchestrator. 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/luckeyfaraday/frontier-orchestrator/main/.claude/skills/orchestrate-specialists/SKILL.mdgit clone --depth 1 https://github.com/luckeyfaraday/frontier-orchestratorWrote 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/luckeyfaraday/frontier-orchestrator/orchestrate-specialists)<a href="https://agentmods.dev/skills/luckeyfaraday/frontier-orchestrator/orchestrate-specialists"><img src="https://agentmods.dev/badge/skills/luckeyfaraday/frontier-orchestrator/orchestrate-specialists/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/luckeyfaraday/frontier-orchestrator/orchestrate-specialists"><img src="https://agentmods.dev/badge/skills/luckeyfaraday/frontier-orchestrator/orchestrate-specialists.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 | $0.00077 | $0.00889 |
| Opus 5.5 | $0.00031 | $0.00356 |
| Sonnet 5.5 | $0.00015 | $0.00178 |
| Haiku 4.5 | $0.00008 | $0.00089 |
Grade A, and why
orchestrate-specialists 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 1mo 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrate Specialists
Act as the lead engineer. Decompose work, define contracts, delegate bounded tasks, inspect the resulting changes, and own final integration and verification.
Use these MCP tools:
mcp__frontier-orchestrator__specialist_status: verify all three CLIs are available.mcp__frontier-orchestrator__delegate_backend: send backend work to Codex.mcp__frontier-orchestrator__delegate_frontend: send design and frontend work to Kimi.mcp__frontier-orchestrator__delegate_build: send domain-neutral tooling and mechanical maintenance work to Grok Build.
Read routing-contract.md when the task is mixed, the ownership boundary is unclear, or parallel implementation is being considered.
Route work
Send to Codex:
- APIs, services, databases, migrations, auth, queues, jobs, infrastructure
- security, backend performance, data integrity, backend-focused tests
- server-side architecture and implementation review
Send to Kimi:
- product and interaction design, information architecture, visual direction
- components, styling, responsiveness, accessibility, animation, client state
- frontend architecture, implementation, and visual/frontend review
Send to Grok Build:
- build configuration, dependency and toolchain upgrades
- CI, release automation, and generated boilerplate
- mechanical repository-wide transformations and test or lint cleanup
Route by ownership before optimizing for speed:
- backend behavior belongs to Codex, even when the change is straightforward
- frontend or UX behavior belongs to Kimi, even when the change is straightforward
- Grok is eligible only for the domain-neutral work above, unless the user explicitly requests Grok
- never select Grok solely because it is faster
Keep with Claude:
- task decomposition and priorities
- shared contracts and cross-stack decisions
- resolving contradictory specialist advice
- reviewing diffs, integrating changes, and final verification
- user communication
What ships with it
2 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.
- 1mo ago First seen · 89 lines · 77 tokens per session scan A 099f2dad8d25
orchestrate-specialists is a skill published in the GitHub repository luckeyfaraday/frontier-orchestrator (8 stars, last pushed 3mo ago), licensed MIT. It adds 77 tokens to every session and 889 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 2026-08-31.
Other skills, from other repositories
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
moai-lane-watchdog
One lane stall watchdog iteration: measure lane progress on three channels, classify the stall cause, apply the remedy or resolve the judgment through the decision ladder — instead of waiting on a reply — then record the outcome and report. Reads the unified --auto doctrine at…
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…
blueprint-cloudflare-scaffold
Lay out a Worker with D1 and static Vue assets, with tests that run inside the Workers runtime.