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 agentmods add skills/blueprintos/analysis-to-delivery/executing-plansnpx skills add BlueprintOS/analysis-to-delivery --skill executing-plansgit clone --depth 1 https://github.com/BlueprintOS/analysis-to-deliveryWrote 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/blueprintos/analysis-to-delivery/executing-plans)<a href="https://agentmods.dev/skills/blueprintos/analysis-to-delivery/executing-plans"><img src="https://agentmods.dev/badge/skills/blueprintos/analysis-to-delivery/executing-plans.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 | $0.00046 | $0.00788 |
| Opus 5 | $0.00023 | $0.00394 |
| Sonnet 5 | $0.00009 | $0.00158 |
| Haiku 4.5 | $0.00005 | $0.00079 |
Grade A, and why
executing-plans 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 4d 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.
What it actually says
Executing-Plans(桥接到 superpowers)
Contract
- Inputs: writing plan, passing task tests, implementation diff
- Outputs: commit history and 5-question retrospective / knowledge updates
- Gates: tests pass; verification command recorded; commit or explicit handoff state exists
- Required disciplines:
stage-gate - Next: next
/tddtask or/verification-before-completion
本仓库不维护此 skill 的内容。完整纪律请读:
<SUPERPOWERS_SKILL_ROOT>/executing-plans/SKILL.md
何时调
- tdd 通过后,逐步 commit
- 每个 writing-plans 子任务 GREEN 后
衔接点
- 产出:commit history + 5 问复盘(沉淀到知识库)
- 下一步:下一任务(回到
/tdd)或/verification-before-completion - 门控:
disciplines/stage-gate第 3 层(commit + 复盘 + 沉淀三件套)
降级方案(superpowers 未装时)
如果 <SUPERPOWERS_SKILL_ROOT>/executing-plans/ 不存在,按以下 4 步执行 + 复盘:
1. 一次一个任务
- 从 plan 第 1 个未被 blocked 的任务开始
- 走
/tdd红绿循环直到 GREEN - ❌ 跳任务 = 中间某个依赖没建,后面全崩
2. commit 前 3 件套
| 件 | 内容 | 标志 |
|---|---|---|
| Verify | 跑完整验证命令看到 0 失败 | "VERIFIED:" 在 commit msg |
| Test | RED→GREEN 转换记录在 commit msg | 让人能复现 |
| 复盘 | 5 问复盘填到 commit body 或 PR | 沉淀到知识库 |
3. 5 问复盘模板
每次 commit 后回答 5 问:
- 实际用时 vs 估计:偏差多少?为什么?
- 遇到什么意外:踩了什么坑?
- 有什么可以做得更好:下次的规则/工具变更?
- 学到什么新知识:要写入知识库哪一篇?
- 下一步动作:接哪个任务 / 是否需要回头改 plan?
4. 进入下一个任务或停
- 下一个任务 → 回到
/tdd - 全部完成 → 走
/verification-before-completion - 卡住 → 停下,把 5 问复盘写到
RETRO_<topic>.md,向用户汇报
最小纪律摘要
- 不跳任务:plan 顺序有依赖,跳 = 后面崩
- commit 前必 verify:
verification-before-completion5 步铁律 - 5 问不复盘 = 知识不沉淀:下次再踩同一个坑
- 卡住就停,不要硬刚:停 > 撞墙
安装提示
npx skills@latest add obra/superpowers-executing-plans
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.
- 4d ago First seen · 78 lines · 46 tokens per session scan A 7ac379c85f17
executing-plans is a skill published in the GitHub repository BlueprintOS/analysis-to-delivery (26 stars, last pushed 2mo ago), licensed MIT. It adds 46 tokens to every session and 788 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.
Other skills, from other repositories
openspec-explore
Enter explore mode - a thinking partner for exploring ideas, investigating problems, and clarifying requirements. Use when the user wants to think through something before or during a change.
release-openspec
Use this skill when releasing OpenSpec: audit merged work and changeset coverage, decide whether a catch-up changeset PR is needed, prepare or resume the Changesets Version Packages PR, cut a beta or stable release, verify publishing, and polish GitHub release notes. Also use when asked whether an open release PR is…
openspec-update-change
Update an OpenSpec change by revising its existing planning artifacts and keeping them coherent with one another. Use when the user wants to revise a change's plan, fold new decisions into it, or reconcile its artifacts after an edit. Never edits code.
openspec-new-change
Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach.
atomicmail
Read and write email through the Atomic Mail from an AI agent. Handles proof-of-work authentication and JMAP so the agent thinks in JMAP method calls. Use when the user asks to register an email inbox, list mailboxes, fetch or send email.
hermesoffice-decks
Produce presentations in HermesOffice Slides — the plandeck/generatedeck pipeline, native element editing, and the templates/decks style specs (modern, elegant, professional, keynote-speaker, minimal, tech-dark, investor-pitch, workshop). Load for any request that creates or restyles a deck.