Borrowing it
Nothing to install: this file belongs to open-software-network/os-clovy. 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/open-software-network/os-clovy/main/.agents/skills/repo-orchestrate/SKILL.mdgit clone --depth 1 https://github.com/open-software-network/os-clovyWrote 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/open-software-network/os-clovy/repo-orchestrate)<a href="https://agentmods.dev/skills/open-software-network/os-clovy/repo-orchestrate"><img src="https://agentmods.dev/badge/skills/open-software-network/os-clovy/repo-orchestrate/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/open-software-network/os-clovy/repo-orchestrate"><img src="https://agentmods.dev/badge/skills/open-software-network/os-clovy/repo-orchestrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00132 | $0.00970 |
| Opus 5 | $0.00066 | $0.00485 |
| Sonnet 5 | $0.00026 | $0.00194 |
| Haiku 4.5 | $0.00013 | $0.00097 |
Grade A, and why
repo-orchestrate 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 9d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo orchestrate
Full-workflow delegation. repo-delegate hands off one scoped brief;
this hands off the whole loop — the chosen harness is the orchestrator
and validator, following repo-build-pr end to end. Same structure as the
sibling skills: one prompt template (PROMPT.md), one runner per
harness, a template for adding more.
Trust model — read before dispatching
The orchestrator commits on a branch it creates, runs your toolchain, and in publish mode pushes with your credentials and opens a PR. Two levels:
- Default (no
--publish): build + validate + review, stop before any push. Codex runs in aworkspace-writesandbox (network enabled forpnpm install --frozen-lockfile); Claude runsacceptEditswith a git/pnpm/cargo allowlist. The caller inspects the worktree and publishes. --publish: the orchestrator maygit pushandgh pr create --draft(never mark ready, never merge). On Codex this requiresdanger-full-access(the workspace sandbox cannot reach your ssh agent); on Claude the allowlist gainsgit pushandgh pr. Only use on tasks and prompts you wrote yourself.
Either way the orchestrator's report is a claim; the worktree diff, gate output, and battery verdicts are the evidence.
How
-
Write the build prompt to a file — exactly what you would type after
/repo-build-pr: objective, constraints, acceptance criteria, scope boundaries. Headless orchestrators cannot ask clarifying questions, so answer the obvious ones in the prompt; anything left open is taken conservatively and recorded as an assumption in the report/PR body. -
Pick the orchestrator harness and dispatch (from the repo root of the main checkout):
scripts/run-codex.sh -t <build-prompt.md> [-C <repo-root>] [-b <base>] [--publish] [-o <out>] scripts/run-claude.sh -t <build-prompt.md> [same flags]--dry-runprints the filled orchestrator prompt. Runs take long — dispatch in the background and read the-oreport file. -
Verify: read the report, then the worktree diff and battery verdicts yourself. Default mode: publish with your own hands. Publish mode: check the draft PR before requesting reviews.
What ships with it
5 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.
- 9d ago First seen · 83 lines · 132 tokens per session scan A 8113cbfcaeb1
repo-orchestrate is a skill published in the GitHub repository open-software-network/os-clovy (357 stars, last pushed yesterday), licensed MIT. It adds 132 tokens to every session and 970 once invoked, about $0.0007 per session on Opus 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.
Other skills, from other repositories
personal-commands
Edit hex.config.ts, not .hex-sdk. Config and installed dependencies execute with the user's normal permissions; use only trusted packages and avoid network, filesystem, environment, or subprocess access unless the requested command requires it. Run bun run check after editing.
hex-personal-commands
Configure HEX personal voice commands, voice-dictation control phrases, and deterministic transcript transformations. Use when the user wants to add or change commands or transformations for the HEX macOS voice app.
macparakeet-stt
Use when the user asks to transcribe audio or video, search MacParakeet's local speech library, retrieve cited transcript segments or knowledge cards, or inspect and manage saved meeting artifacts on macOS Apple Silicon.
murmur-mcp
Query Murmur's local read-only MCP server for gated, indexed knowledge — semantic + full-text search over meetings and notes, entity dossiers, structured transcripts, open-commitment rollups, and typed note-folder database queries. Prefer this over grepping raw vault files. Use when you need to find, retrieve, or…
murmur-vault
How to coexist with Murmur's notes in an Obsidian vault — note anatomy, front-matter keys, managed sections you must never edit, wikilink discipline, entity stubs, where files live, the locked-folder disappeared-file rule, and the add-freely/prefer-append coexistence contract. Use when reading, editing, or creating…
frame-macos-notification
Realistic macOS notification banner with app icon, title, and body, suited to video overlays or product teasers.