speclite-goal-orchestrator-epic-story-code-review-runner

speclite-goal-orchestrator-epic-story-code-review-runner is a skill for Claude Code from flanliulf/SpecLite. It costs 94 tokens per session (1,784 once invoked), scanned A, original, MIT.

An Epic Story code-review runner coordinates development and code review for Stories within an Epic. It moves one Story at a time through development, review, evaluation, fixes, verification, and closeout using structured records.

In plain words
What is it for?
Use it for a strict serial Epic workflow involving fresh agents, review findings, evaluator decisions, fixes, finalization, tracker updates, and a local commit.
Why use it?
It prevents out-of-order work, stale review evidence, and ambiguous approval decisions across a multi-Story change. It also limits repeated review cycles and checks the conditions for safely closing the work.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Good fit Use it for a strict serial Epic workflow involving fresh agents, review findings, evaluator decisions, fixes, finalization, tracker updates, and a local commit.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/flanliulf/speclite/speclite-goal-orchestrator-epic-story-code-review-runner
Install

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.

Any agent
npx skills add flanliulf/SpecLite --skill speclite-goal-orchestrator-epic-story-code-review-runner
Clone the repo
git clone --depth 1 https://github.com/flanliulf/SpecLite

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 speclite-goal-orchestrator-epic-story-code-review-runner

README.md
[![agentmods](https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-goal-orchestrator-epic-story-code-review-runner/github.svg)](https://agentmods.dev/skills/flanliulf/speclite/speclite-goal-orchestrator-epic-story-code-review-runner)
Your own site
<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-goal-orchestrator-epic-story-code-review-runner"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-goal-orchestrator-epic-story-code-review-runner/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 speclite-goal-orchestrator-epic-story-code-review-runner

Your own site · 80×15
<a href="https://agentmods.dev/skills/flanliulf/speclite/speclite-goal-orchestrator-epic-story-code-review-runner"><img src="https://agentmods.dev/badge/skills/flanliulf/speclite/speclite-goal-orchestrator-epic-story-code-review-runner.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,784 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 $0.00094 $0.01784
Opus 5.5 $0.00038 $0.00714
Sonnet 5.5 $0.00019 $0.00357
Haiku 4.5 $0.00009 $0.00178

Measured 1mo ago against content hash 011f34783a84, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

speclite-goal-orchestrator-epic-story-code-review-runner 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 1mo 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.

assets/source/speclite/sdlc-skills/4-implementation/speclite-goal-orchestrator-epic-story-code-review-runner/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Speclite Goal Orchestrator Epic Story Code Review Runner(Epic Story 开发与代码审查执行器)

Overview(概述)

本 Skill 是 Epic 粒度 Story 开发与 CR 闭环的全局编排层。它只负责目标拆解、strict serial 调度、Flow Gate、CR v2 状态机、收敛控制、状态同步和最终本地提交,不替代被编排 Skill 的内部能力。

同一时间只能推进一个 Story、一个外层 sub-agent、一个状态迁移。所有 current decision 必须来自结构化 frontmatter,不得解析“通过”“不通过”“Approved”等 prose 关键词。

Activation Boundary(激活边界)

仅在用户要求以 Epic 或明确 Story 集合为范围,执行 development → review → evaluate → fix/verify → closeout 的 strict-serial 闭环,并要求 fresh outer sub-agent、goal records 或最终本地提交时使用本 Skill。

以下情况不要使用本 Skill:

  • 只开发单个 Story 且不要求完整 CR 闭环;
  • 只运行一次 reviewer、evaluator、fixer 或 finalizer;
  • 用户只询问状态,未授权开发、状态推进或提交;
  • 用户明确要求并行推进多个 Story;
  • 任务属于 Story Review,应使用对应 SR runner。

Core Capabilities(核心能力)

  • 严格串行编排:每次只推进一个 Story 和一个外层状态迁移。
  • 结构化 CR v2 路由:按 exact schema、verdict、scope hash 和 round binding 路由。
  • 有界收敛:按 finding fingerprint、quorum、churn 与 stop-loss 机械收敛。
  • 可恢复执行:根据 current structured artifact 和 goal records 决定唯一下一状态,不重复已完成步骤。
  • 安全收口:校验 evidence freshness、TODO 映射、tracker 原子同步与本地提交边界。

Contract(共享契约)

执行前必须完整读取 {skills-root}/speclite-code-review-contract/references/cr-contract.md。独立的 speclite-code-review-contract package 是 CR01–06 与 runner 的唯一规范性共享契约 owner,定义 identity、路径、scope manifest、artifact schema、verdict、finding fingerprint、layer quorum、round binding、state machine、freshness 和 TODO/rules governance。

共享契约不可读或关键字段无法解析时 HALT。

Inputs(输入)

  • epicId:目标 Epic,例如 8。
  • storyScope:Epic 全部 Story 或用户明确指定的子集。
  • projectRoot:目标项目根目录。
  • modelPolicy:默认使用当前环境配置;如用户指定模型则遵从,并如实记录实际模型。
  • commitPolicy:默认中文 Conventional Commit、本地提交、不 push。
  • confirmationPolicy:explicit | preauthorized;默认 explicit,只能由用户请求或已确认授权范围切换。

无法识别 Epic、Story 列表、project root 或授权范围时 HALT 并询问,不得猜测。

Runtime Activation(运行时激活)

  1. 运行 speclite resolve config --project-root {projectRoot}。
  2. 读取 merged planning_artifacts、implementation_artifacts 和 workflow tracker 配置。
  3. 将当前 Skill 目录父目录解析为 {skills-root}。
  4. 读取 {skills-root}/speclite-code-review-contract/references/cr-contract.md。
  5. 运行一次 speclite resolve cr-directory --story-id {storyId} --review-series {reviewSeries} --project-root {projectRoot},冻结 crDir 并传给 CR01–06;continuation=block 时 HALT。
  6. 解析失败、关键路径为空或 Story identity 冲突时 HALT;config.toml.example 和历史默认目录不能作为 fallback。

Read the full file on GitHub · 114 lines

Files

What ships with it

3 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. 1mo ago First seen · 114 lines · 94 tokens per session scan A 011f34783a84

Subscribe to this mod's changes

speclite-goal-orchestrator-epic-story-code-review-runner is a skill published in the GitHub repository flanliulf/SpecLite (4 stars, last pushed 2d ago), licensed MIT. It adds 94 tokens to every session and 1,784 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-16.

Related

Other skills, from other repositories

PR Standards

Pull request description, review depth, and merge standards so every PR carries enough context to review and merge safely.

niels-emmer/myace · 25 tokens

validate-changes

Evaluate staged changes using LLM-as-a-Judge before committing.

FlorianBruniaux/claude-code-ultimate-guide · 16 tokens

signing-preflight

Before the first commit of a session, check that commit signing will work — the key is loaded and unlocked — and ask the operator to unlock it once, up front, instead of discovering it after a hundred unsigned commits. Never disables signing silently, never re-signs history without asking. Use at the start of…

avelikiy/great_cto · 105 tokens

ase-repo-review

Perform a holistic, human-reviewer-style critique of the currently staged Git changes (or, with --unstaged, of the unstaged and untracked changes, with --branch, of a branch against its base, or, with --commit, of a single commit) and emit an approve/reject verdict with prioritized, severity-tagged, line-cited…

rse/ase · 111 tokens

spec-finish

Post-implementation completion workflow for Spec-backed Plans. Use after spec-implement completes to validate, review, create stacked commits, and open a PR via code-pull-request. Triggers only with an active Spec-backed Plan after spec-implement completes, including when the user says "finish", "done", or "complete"…

martinffx/atelier · 73 tokens

spec-loop

Run an approved Spec-backed Plan (design.md and plan.json both present) unattended to a draft PR: implement and review each batch with fresh subagents, commit, then finish with one whole-branch review. Use when the user says "run it to the end" or "implement everything and open a PR".

martinffx/atelier · 66 tokens