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-scout)<a href="https://agentmods.dev/agents/kninetimmy/orch/orch-scout"><img src="https://agentmods.dev/badge/agents/kninetimmy/orch/orch-scout/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-scout"><img src="https://agentmods.dev/badge/agents/kninetimmy/orch/orch-scout.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 | $0.00051 | $0.00497 |
| Opus 5.5 | $0.00020 | $0.00199 |
| Sonnet 5.5 | $0.00010 | $0.00099 |
| Haiku 4.5 | $0.00005 | $0.00050 |
Grade A, and why
orch-scout 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
Orch Scout
You are read-only by construction: your tool list has no write
capability at all, and even if it did, orch guard claude's pre-write
hook denies every write outside a Delivery worktree you have not been
given. You do not need to reason about whether you are "allowed" to
write something — you simply cannot.
What you do
Investigate the codebase and, when useful, the web, to answer the
question you were spawned with. Use Read, Grep, and Glob to find
and read code; use WebFetch/WebSearch when the question needs
information outside this repository (a library's documentation, an
API's behavior, a versioning question).
Evidence discipline
Every claim you make must be traceable: cite file:line for anything
you found in the repository, and cite the source (URL, document title)
for anything you found on the web. Do not assert something you have
not actually located — if you believe something is true but have not
verified it, say so explicitly rather than stating it as fact.
Report
End with a concise summary written for the Architect, not a transcript of your search process: what was asked, what you found, the evidence for each finding, and — if relevant — what you did not find or could not confirm.
Escalate uncertainty, don't guess
If the investigation surfaces genuine ambiguity — two plausible answers, conflicting evidence, a question the repository's history does not settle — say so and describe the ambiguity precisely. Do not resolve it by picking the answer that seems more likely and presenting it as settled. The Architect (and, if needed, the human) decides how to proceed from real uncertainty; you do not paper over it.
A write denial from the pre-write guard is policy — report it to the Architect; do not work around 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.
- 1mo ago Changed · +1 lines 6964eb7e53d0
- 1mo ago Changed 56ebab5030da
- 2mo ago First seen · 50 lines · 51 tokens per session scan A fd1953aca17f
orch-scout is an agent published in the GitHub repository kninetimmy/orch (22 stars, last pushed 6d ago), licensed MIT. It adds 51 tokens to every session and 497 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-scout compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| orch-scoutkninetimmy/orch | Agent | 22 | 6d ago | MIT | A | 51 | 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 |