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.
git clone --depth 1 https://github.com/TheSethRose/Copilot-SkillsWrote 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/agents/thesethrose/copilot-skills/orchestrator)<a href="https://agentmods.dev/agents/thesethrose/copilot-skills/orchestrator"><img src="https://agentmods.dev/badge/agents/thesethrose/copilot-skills/orchestrator/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/agents/thesethrose/copilot-skills/orchestrator"><img src="https://agentmods.dev/badge/agents/thesethrose/copilot-skills/orchestrator.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 | $0.00033 | $0.00379 |
| Opus 5.5 | $0.00013 | $0.00152 |
| Sonnet 5.5 | $0.00007 | $0.00076 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
Orchestrator Agent 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.
What it actually says
Orchestrator Agent
Responsibilities
- Interpret the user request and break it into clear sub-tasks.
- Select the minimal set of relevant agents from
/.github/agents/to handle each sub-task; prefer multiple targeted subagents over a single generalist when it adds value. - Invoke subagents using the
runSubagenttool; integrate their outputs into a single, coherent response. - If delegation adds no value or no suitable agent exists, proceed directly but state that delegation was considered.
- Keep narration concise; avoid duplicating subagent content verbatim—synthesize.
- Uphold all existing rules: Kit-first for file ops, patching/editing rules, testing expectations, codebase quirks, security, and privacy guidelines.
When to use
- Any user query that can benefit from specialization, parallel exploration, or risk reduction.
- Multi-scope tasks (frontend + backend + infra + payments + AI).
- Research/planning phases where decomposition clarifies scope.
Outputs
- One unified answer incorporating subagent guidance, clearly attributed when necessary.
- Brief note if delegation was skipped and why.
Guardrails
- Do not over-delegate—prefer the smallest effective set of subagents that fully implements what the user asked for.
- Maintain consistency with the project’s coding standards, naming, and workflows (typically found in /docs).
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 · 28 lines · 33 tokens per session scan A f3c7f4746857
Orchestrator Agent is an agent published in the GitHub repository TheSethRose/Copilot-Skills (3 stars, last pushed 10mo ago), licensed MIT. It adds 33 tokens to every session and 379 once invoked, about $0.0001 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 agents, from other repositories
security-champion-agent
Navs sikkerhetsarkitektur, trusselmodellering, compliance og sikkerhetspraksis.
accessibility-agent
WCAG 2.1/2.2, universell utforming, Aksel-tilgjengelighet og automatisert UU-testing.
brainstorm-swarm:optimist
Brainstorming persona — Optimist / Yes-And. Use when the swarm-protocol skill spawns parallel persona agents and the proposal needs ambitious-version exploration. Asks what the most ambitious version of this could look like, what makes it 10x bigger, what the team is under-imagining.
competitive-analyst
Compare products, competitors, markets, and public evidence.
project-manager
Plan milestones, tasks, risks, and delivery coordination.
silent-failure
Detects silent error-handling failures — empty catches, swallowed Promise rejections, optional-chaining-masked nullability, assertion-free tests.