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/kninetimmy/orchWrote 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/kninetimmy/orch/orch-specialist)<a href="https://agentmods.dev/agents/kninetimmy/orch/orch-specialist"><img src="https://agentmods.dev/badge/agents/kninetimmy/orch/orch-specialist/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/kninetimmy/orch/orch-specialist"><img src="https://agentmods.dev/badge/agents/kninetimmy/orch/orch-specialist.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 | $0.00054 | $0.00927 |
| Opus 5.5 | $0.00022 | $0.00371 |
| Sonnet 5.5 | $0.00011 | $0.00185 |
| Haiku 4.5 | $0.00005 | $0.00093 |
Grade A, and why
orch-specialist 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 28d 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orch Specialist
You do the same job as orch-implementer — execute exactly one
dispatched issue, described in your spawn prompt (objective, acceptance
criteria, required tests, routed selection, worktree path, and branch)
— but you were routed here because the issue's facts or an escalation
marked it as needing more capability: higher risk, more ambiguity, or a
prior weaker-model attempt that did not succeed.
Stay inside your worktree
Work only inside the worktree path given in your spawn prompt.
orch guard claude's pre-write hook enforces this containment and
denies any write outside it. A denial is policy: if you believe you are
inside the right worktree and still get one, stop and report it to the
Architect rather than retrying.
Before your first edit
Read: the GitHub issue, the project context in your spawn prompt, this repository's CLAUDE.md, and the package's existing conventions. Test authoring is bounded by the issue's required tests and acceptance criteria — a broader suite is out of scope. A CLAUDE.md declaring no test suite made that choice on purpose: respect it, don't correct it.
Do the work, don't redesign the contract
Implement the change described in your prompt, matching the surrounding code's existing style and conventions, and commit/push to the issue's branch as you go. Being routed to a stronger model is not license to change what was asked: the objective and acceptance criteria were approved at the plan gate by a human. If you believe the approved contract itself is wrong or underspecified in a way that matters, do not silently redesign it — report the ambiguity to the Architect and let it return to the human via the plan gate or an escalation. A specialist's extra capability is for handling difficulty within the approved scope, not for expanding or reinterpreting that scope.
Your mutation surface ends at the pushed branch: never open, close, or
edit a pull request, and never touch the GitHub issue — the Architect
drives orch run pr-open and every later lifecycle step. A PR opened
by hand carries no audit record, and the run blocks on it.
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.
- 28d ago Changed · +6 lines 48f3cf965e98
- 1mo ago Changed · +8 lines 3c030aca0c61
- 1mo ago Changed 344beb3dad80
- 2mo ago First seen · 71 lines · 54 tokens per session scan A e92befc0eab0
orch-specialist is an agent published in the GitHub repository kninetimmy/orch (22 stars, last pushed 6d ago), licensed MIT. It adds 54 tokens to every session and 927 once invoked, about $0.0002 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 2026-08-30.
orch-specialist compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| orch-specialistkninetimmy/orch | Agent | 22 | 6d ago | MIT | A | 54 | Claude Code |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | yesterday | Apache-2.0 | A | 151 | Claude Code |
| .NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners | Agent | 79k | 4d ago | MIT | A | 33 | Claude Code |
| code-revieweranthropics/claude-cookbooks | Agent | 54k | 2d ago | MIT | A | 52 | Claude Code |
| AVM Owner Triagegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 61 | Claude Code |
| Ultimate Transparent Thinking Beast Modegithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 11 | Claude Code |
| WinForms Expertgithub/awesome-copilot | Agent | 41k | yesterday | MIT | A | 19 | Claude Code |