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.
npx skills add rordi-ai/loopbreaker --skill orchestrate-deliverygit clone --depth 1 https://github.com/rordi-ai/loopbreakerWrote 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/rordi-ai/loopbreaker/orchestrate-delivery)<a href="https://agentmods.dev/skills/rordi-ai/loopbreaker/orchestrate-delivery"><img src="https://agentmods.dev/badge/skills/rordi-ai/loopbreaker/orchestrate-delivery/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/rordi-ai/loopbreaker/orchestrate-delivery"><img src="https://agentmods.dev/badge/skills/rordi-ai/loopbreaker/orchestrate-delivery.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 | $0.00084 | $0.00886 |
| Opus 5 | $0.00042 | $0.00443 |
| Sonnet 5 | $0.00017 | $0.00177 |
| Haiku 4.5 | $0.00008 | $0.00089 |
Grade A, and why
orchestrate-delivery 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 10d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrate Delivery
Run the delivery pipeline as three separated roles so that no context ever grades its own work. The frozen behavior contract is the only interface between them.
Roles
- Root orchestrator — the session reading this skill, on the strongest available model (Claude Code: Fable). It owns gate checks, contract imports, worktree merges, evidence recording for integration-level proof, and the ship conversation. It does not implement work units and never records review passes for changes it authored.
- Implementation workers — one subagent per work unit on a Sonnet-class
model, each in its own git worktree (Claude Code: spawn the
impl-workeragent withisolation: "worktree"). A worker receives the issue ID, its one work unit, the enforced behaviors it owns, and the proof plan. It implements, tests, and reports; it must not edit behavior children, planning state, or review state. - Independent reviewer — the Codex CLI, a different vendor and model family,
invoked non-interactively with the Loopbreaker MCP server injected. It runs
review-planningbefore implementation andreview-invariantsafter, and it records its own passes, findings, and evidence directly over MCP. Follow references/codex-review.md exactly for the pinned invocation; do not improvise flags.
Protocol
- Bind.
loopbreaker link ISSUEbefore anything else, in the root and in every worker worktree. The admission hook is keyed to that binding; an unlinked session fails open and every gate below is decorative. - Gate. Call
delivery_readiness. Drivediscovery-interviewfirst when the issue has no approved discovery record, thenshape-strategy,plan-feature, and an independentreview-planning(via the reviewer role) untilimplementation.admittedis true. Never start workers before admission. - Fan out. Spawn one worker per work unit in parallel. Give each the frozen contract excerpt it owns, verbatim. Workers changing scope report back for a contract decision; they do not resolve it locally.
- Integrate. Merge worktrees and run the repository verification. Each
behavior is verified by
loopbreaker prove, whose verdict comes from its registered harness's exit code — the orchestrator records no verdicts of its own. Workers own writing, registering and binding their behaviors' harnesses, and must prove them RED before implementing. - Review. Invoke the reviewer for pass 1. Repair findings by re-dispatching the owning worker with the finding's smallest fix, then invoke the reviewer for pass 2, and pass 3 as decision only. Three passes bound both review stages; there is no pass 4.
- Ship. Read
review_ship_statusand copy its disposition literally. Review completion never implies shipping readiness. A human authorizes any waiver.
What ships with it
2 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.
- 10d ago First seen · 65 lines · 84 tokens per session scan A 92beee428e37
orchestrate-delivery is a skill published in the GitHub repository rordi-ai/loopbreaker (3 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 886 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.