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 aldianriski/lean-flow --skill orchestratorgit clone --depth 1 https://github.com/aldianriski/lean-flowWrote 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/aldianriski/lean-flow/orchestrator)<a href="https://agentmods.dev/skills/aldianriski/lean-flow/orchestrator"><img src="https://agentmods.dev/badge/skills/aldianriski/lean-flow/orchestrator.svg" alt="Measured on agentmods" 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 | $0.04501 |
| Opus 5 | $0.00042 | $0.02250 |
| Sonnet 5 | $0.00017 | $0.00900 |
| Haiku 4.5 | $0.00008 | $0.00450 |
Grade A, and why
orchestrator 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 7d 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 — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
orchestrator
Gate-driven execution loop. Coordinate the work; restate intent as a verifiable goal first. Humans approve gates — never self-approve. No specialist agents: gates are inline checklists and review is a structured self-pass.
Mode dispatch
| Mode | Gates | Use when |
|---|---|---|
quick |
G1 | single task, small, low risk |
mvp |
G1 + G2 | feature work, medium+, multi-step |
sprint-bulk |
G1+G2 once | auto-loop the Active Sprint task list |
overnight |
G1+G2 pre-signed | canonical name for the unattended headless run of a promoted Plan — sprint-bulk under the Part 0 authority contract and the Part 0b continuation contract. Aliases, all still accepted: night-run · unattended · sprint-bulk unattended |
Intake routing — a mode keyword selects the mode, it never bypasses these routing checks. Run them on every invocation, named mode or not:
- No tracked task → run
/task-decomposerfirst, then return here. - Intent too foggy to slice (decisions unknown — no acceptance criteria writable yet) →
/task-decomposerfog-mode (--fog): map the decisions before forcing tasks. - Task is in an active sprint → default to the sprint mode (or
quickfor a single one). - Task is only in the Backlog (not in any active sprint) → don't silently build: surface the choice as a popup —
/lean-doc-generator promoteit into a sprint, or proceed as an explicitquickone-off (never slide decompose → build unrecorded). - Asked to start a night run on anything that isn't already a promoted Plan → you are the interactive launcher, not the run: do feed → promote → pre-flight here, gates and all, and fire the trigger only once pre-flight is green. Never spawn first (→
${CLAUDE_SKILL_DIR}/references/night-run.mdPart 1a).
G1 — Scope gate (all modes, always runs)
Confirm before touching code. BLOCK if any answer is "unknown":
- Goal restated as one verifiable sentence ("done when …")
- Size estimated S / M / L — an L splits before proceeding
- Files likely touched listed; blast radius understood — for unfamiliar / mature code, recon via the
Exploreagent (read existing impl + tests + deps in its own context; keeps this loop lean) - Out-of-scope explicitly named (what this task will NOT do)
- Assumptions surfaced and confirmed where they affect behavior
What ships with it
4 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.
- 7d ago First seen · 117 lines · 84 tokens per session scan A fa6bbbc7c197
orchestrator is a skill published in the GitHub repository aldianriski/lean-flow (5 stars, last pushed 8d ago), licensed MIT. It adds 84 tokens to every session and 4,501 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…