agentmods.dev

story-direction-review

story-direction-review is a skill for Claude Code, Codex from hxy91819/mason-skills. It costs 27 tokens per session (719 once invoked), scanned A, original, MIT.

A review guide for checking whether a completed project story still supports the wider project goal. It compares the finished work with the agreed scope, evidence, dependencies, and remaining tasks.

In plain words
What is it for?
Use it after a story is finished to decide whether work should continue, receive a small follow-up prompt, gain an inserted task, or require a broader replanning decision.
Why use it?
It helps catch work that passed local checks but changed direction, left an important result uncovered, or invalidated assumptions for later tasks. It keeps completed history intact while identifying needed planning changes.

Skill for Claude CodeCodex

Written for Claude Code and Codex: disable-model-invocation in frontmatter, but also agents/openai.yaml present. Also seen: $skill-name invocation.

not rated 3repo changed 1mo ago A scan 27 tokens original MIT

Good fit Use it after a story is finished to decide whether work should continue, receive a small follow-up prompt, gain an inserted task, or require a broader replanning decision.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/hxy91819/mason-skills/story-direction-review
View source ↗ hxy91819/mason-skills
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 hxy91819/mason-skills --skill story-direction-review
Clone the repo
git clone --depth 1 https://github.com/hxy91819/mason-skills

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 story-direction-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/hxy91819/mason-skills/story-direction-review/github.svg)](https://agentmods.dev/skills/hxy91819/mason-skills/story-direction-review)
Your own site
<a href="https://agentmods.dev/skills/hxy91819/mason-skills/story-direction-review"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/story-direction-review/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 story-direction-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/hxy91819/mason-skills/story-direction-review"><img src="https://agentmods.dev/badge/skills/hxy91819/mason-skills/story-direction-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 27 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 719 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 $0.00027 $0.00719
Opus 5.5 $0.00011 $0.00288
Sonnet 5.5 $0.00005 $0.00144
Haiku 4.5 $0.00003 $0.00072

Measured 1mo ago against content hash 54c2bd510f64, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

story-direction-review 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.

common-skills/story-direction-review/SKILL.md · 58 lines

What it actually says

Story Direction Review

这是流程类 Skill，仅在用户显式调用 $story-direction-review 时运行。large-task-orchestrator 在 需要大局判断（是否插入 Story、是否重规划）时，也会另派线程并在任务里显式调用本 Skill；它的常规 Validator 只逐条核对 Acceptance，不走本 Skill。默认只读；只确认 Story 是否真正完成、方向是否仍 成立。不做代码审查、风格检查或局部重构建议。

建立独立视角

优先由未实现该 Story 的 Validator 执行。先加载 $large-task-planning，再从宿主返回的 Skill 根目录运行 scripts/epic_story.py brief，取得稳定边界、目标 Story、相关黄金案例与直接前置 Handoff；然后运行 status --json 了解后续结果与依赖； 有疑点时查看 SPEC.md、原始证据和代码。不要把 STATUS.md 当成 Agent 状态源。

区分四类事实：稳定 Goal 与用户边界、Story 原意、实际交付与证据、新发现的实现假设。

检查方向

  1. 实际结果是否满足 Story Outcome/Acceptance，还是用局部通过替代了用户结果。
  2. 新事实是否推翻 agent/plan.json 的 Goal、黄金 oracle、边界或后续 Story 前提。
  3. 黄金案例和纵向结果是否有重大遗漏，final_story 是否仍能闭合全部依赖路径。
  4. 下一张 Story 是否能凭自身 Context 与前置 Handoff 开工，而无需发明产品决定。

给出唯一结论

  • CONTINUE：方向和后续前提成立。
  • PATCH：同一 Story 内有明确小遗漏；给出 Worker 可直接使用的修复提示。
  • INSERT_STORY：出现新的独立工程结果；说明插入位置、依赖、验收和最小计划影响。
  • REPLAN：Goal、黄金判据或用户边界失效；列出需要用户决定的一个最小问题。

Validator 不修改文件或状态。若用户另行要求应用结论，由 orchestrator 保留既有 Story ID 和已完成证据； 插入使用 STORY-NN.M；改变 Story Outcome/Acceptance 时递增 intent_version；改变 Goal、黄金判据或 用户边界时先取得用户决定并递增 goal_version。

输出

结论：CONTINUE | PATCH | INSERT_STORY | REPLAN

方向证据：
- <原定结果与实际证据>
- <新事实对后续计划的影响>
- <黄金覆盖或重大遗漏>

计划动作：<无需调整，或最小调整>
下一步提示词：<Worker、orchestrator 或决策人可直接使用的内容>

完成标准：结论唯一、证据可追溯、没有代码审查噪声，下一会话能直接继续或明确停止。

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. 1mo ago Changed · +1 lines 54c2bd510f64
  2. 1mo ago Changed · +2 lines 2418b82b539b
  3. 1mo ago Changed · +1 lines 288a92f5f2a1
  4. 2mo ago Changed · +1 lines f430d7c9d602
  5. 2mo ago Changed · -10 lines · +5 tokens per session 708acd80b7bf
  6. 2mo ago First seen · 63 lines · 22 tokens per session scan A aa00afc4f418

Subscribe to this mod's changes

story-direction-review is a skill published in the GitHub repository hxy91819/mason-skills (3 stars, last pushed today), licensed MIT. It adds 27 tokens to every session and 719 once invoked, about $0.0001 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 2026-08-31.

PlanningProject management
Related

story-direction-review compared with skills from other repositories

story-direction-review next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
story-direction-reviewhxy91819/mason-skillsSkill3todayMITA27Claude Code, Codex
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79kyesterdayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill100kyesterdayApache-2.0A19Claude Code
browser-automationopenclaw/openclawSkill394ktodayMITA36Claude Code
systematic-debuggingobra/superpowersSkill314k4d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code