os-clovy: Skill for Claude Code

.agents/skills/repo-orchestrate/SKILL.md

repo-orchestrate is a skill for Claude Code, Codex from open-software-network/os-clovy. It costs 132 tokens per session (970 once invoked), scanned A, original, MIT.

A tool that hands an entire build-and-review workflow to another coding-agent harness, such as Claude Code or Codex. The chosen agent can create a worktree, implement the task, validate it, and review the result according to the workflow.

In plain words
What is it for?
Running a full feature workflow, including implementation, validation, review, and—when explicitly enabled—pushing a branch and opening a draft pull request.
Why use it?
It lets another agent manage a complete implementation cycle while keeping defined safeguards around branches, checks, commits, and optional publishing.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code; installed under .agents/ (shared by several agents); mentions Codex.

This is open-software-network/os-clovy's own configuration. It tells Claude Code and Codex how to work on os-clovy itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything os-clovy configures →

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/open-software-network/os-clovy/main/.agents/skills/repo-orchestrate/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/open-software-network/os-clovy

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for repo-orchestrate

README.md
[![agentmods](https://agentmods.dev/badge/skills/open-software-network/os-clovy/repo-orchestrate/github.svg)](https://agentmods.dev/skills/open-software-network/os-clovy/repo-orchestrate)
Your own site
<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.

agentmods 80×15 button for repo-orchestrate

Your own site · 80×15
<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>
Per session 132 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 970 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 9d ago against content hash 8113cbfcaeb1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

The scan reads SKILL.md. This mod also ships 3 executable files (scripts/fill-prompt.sh, scripts/run-claude.sh, scripts/run-codex.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

.agents/skills/repo-orchestrate/SKILL.md · 83 lines

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 a workspace-write sandbox (network enabled for pnpm install --frozen-lockfile); Claude runs acceptEdits with a git/pnpm/cargo allowlist. The caller inspects the worktree and publishes.
  • --publish: the orchestrator may git push and gh pr create --draft (never mark ready, never merge). On Codex this requires danger-full-access (the workspace sandbox cannot reach your ssh agent); on Claude the allowlist gains git push and gh 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

  1. 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.

  2. 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-run prints the filled orchestrator prompt. Runs take long — dispatch in the background and read the -o report file.

  3. 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.

Read the full file on GitHub · 83 lines

Files

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.

Changes

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.

  1. 9d ago First seen · 83 lines · 132 tokens per session scan A 8113cbfcaeb1

Subscribe to this mod's changes

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.

Related

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.

anomalyco/hex · 0 tokens

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.

anomalyco/hex · 44 tokens

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.

moona3k/macparakeet · 50 tokens

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-io/murmur · 93 tokens

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…

murmur-io/murmur · 89 tokens

frame-macos-notification

Realistic macOS notification banner with app icon, title, and body, suited to video overlays or product teasers.

nexu-io/open-design · 30 tokens