orchestrator: Skill for Claude Code

.claude/skills/project-readiness/SKILL.md

project-readiness is a skill for Claude Code from c9r-io/orchestrator. It costs 40 tokens per session (463 once invoked), scanned A, original, MIT.

A release-readiness checking procedure for a repository containing Rust code and a React/Tauri desktop interface. It produces a verdict tied to a specific code revision and includes local, documentation, and CI checks.

In plain words
What is it for?
Use it before release to check Rust formatting, tests, and Clippy, validate the GUI build and tests, lint documentation, and compare local results with the latest relevant CI run.
Why use it?
It replaces informal release decisions with evidence from the actual code, tests, quality checks, and GitHub Actions results. Missing deployment files are treated as not applicable rather than assumed to pass.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is c9r-io/orchestrator's own configuration. It tells Claude Code how to work on orchestrator 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 orchestrator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to c9r-io/orchestrator. 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/c9r-io/orchestrator/main/.claude/skills/project-readiness/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/c9r-io/orchestrator

Made for: Claude Code.

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 project-readiness

README.md
[![agentmods](https://agentmods.dev/badge/skills/c9r-io/orchestrator/project-readiness/github.svg)](https://agentmods.dev/skills/c9r-io/orchestrator/project-readiness)
Your own site
<a href="https://agentmods.dev/skills/c9r-io/orchestrator/project-readiness"><img src="https://agentmods.dev/badge/skills/c9r-io/orchestrator/project-readiness/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 project-readiness

Your own site · 80×15
<a href="https://agentmods.dev/skills/c9r-io/orchestrator/project-readiness"><img src="https://agentmods.dev/badge/skills/c9r-io/orchestrator/project-readiness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 463 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.
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 $0.00040 $0.00463
Opus 5 $0.00020 $0.00231
Sonnet 5 $0.00008 $0.00093
Haiku 4.5 $0.00004 $0.00046

Measured 9d ago against content hash 43ca2abf1e84, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

project-readiness 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 1 executable file (scripts/check_local.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.

.claude/skills/project-readiness/SKILL.md · 47 lines

What it actually says

Project Readiness

Produce a revision-pinned, evidence-backed readiness verdict. A missing deployment surface is not applicable, not an implicit pass and not permission to synthesize infrastructure.

Agent Orchestrator Baseline

  1. Record revision and worktree state with git rev-parse HEAD and git status --short.

  2. Run the local readiness helper:

    .claude/skills/project-readiness/scripts/check_local.sh
    
  3. Verify the Rust workspace with the repository's required commands: formatting check, workspace tests, and Clippy with warnings denied.

  4. Verify the Web UI from gui/ with the scripts declared in gui/package.json; include build and tests, and E2E when UI behavior is in scope.

  5. Run scripts/qa-doc-lint.sh so documentation and governance contracts are included.

  6. Inspect the latest relevant GitHub Actions run with gh, and reconcile its required gates with the pinned local revision.

The helper does not reset data, start a daemon, or contact a cluster. State-changing smoke checks require explicit scope.

Optional Generated-Project Checks

If the target repository contains docker/docker-compose.yml, scripts/reset-docker.sh, k8s/base/, or deploy/, verify those exact surfaces. These are project-bootstrap outputs and are absent from the Agent Orchestrator repository.

  • Compose: render config, start only when authorized, check declared health state, and capture bounded logs.
  • Kubernetes: prefer offline kustomize/render checks before any cluster action.
  • Deployment scripts: inspect supported dry-run behavior before execution.

Verdict

Report PASS, FAIL, or NOT APPLICABLE for:

  • revision/worktree
  • Rust format, tests, and lint
  • Web UI tests and build
  • governance docs/gates
  • GitHub Actions
  • runtime smoke checks
  • container/Kubernetes surfaces

For every failure, include the exact command, exit code, smallest useful error excerpt, and rerun command.

Files

What ships with it

1 file 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 · 47 lines · 40 tokens per session scan A 43ca2abf1e84

Subscribe to this mod's changes

project-readiness is a skill published in the GitHub repository c9r-io/orchestrator (21 stars, last pushed 7d ago), licensed MIT. It adds 40 tokens to every session and 463 once invoked, about $0.0002 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.