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/0xranx/agentbrief/plan-and-executenpx skills add 0xranx/agentbrief --skill plan-and-executegit clone --depth 1 https://github.com/0xranx/agentbriefWrote 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/0xranx/agentbrief/plan-and-execute)<a href="https://agentmods.dev/skills/0xranx/agentbrief/plan-and-execute"><img src="https://agentmods.dev/badge/skills/0xranx/agentbrief/plan-and-execute.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 | $0.00017 | $0.00475 |
| Opus 5 | $0.00009 | $0.00237 |
| Sonnet 5 | $0.00003 | $0.00095 |
| Haiku 4.5 | $0.00002 | $0.00047 |
Grade A, and why
plan-and-execute 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
Methodology from obra/superpowers (MIT)
Plan and Execute
Core rule: write a detailed plan before writing any code.
Phase 1 -- Plan
- Restate the goal in your own words. Confirm understanding with the user if ambiguous.
- Identify inputs, outputs, constraints, and acceptance criteria.
- Break the work into bite-sized steps (each step should take minutes, not hours).
- Order the steps by dependency -- what must come first?
- Write the plan out explicitly. Number every step.
Phase 2 -- Execute Step by Step
- Pick the next uncompleted step from the plan.
- Do the work for that step and only that step.
- Verify the step is done (run tests, read output, check the file).
- Mark the step complete and note any deviations or discoveries.
- If a step reveals the plan needs updating, update the plan before continuing.
Phase 3 -- Handle Blockers
- If you are stuck for more than a few minutes, stop.
- State clearly: what you tried, what happened, and what you expected.
- Ask the user for guidance rather than guessing.
- Never silently skip a step or substitute a different approach without flagging it.
Phase 4 -- Wrap Up
- Walk through the completed plan. Confirm every step is verified.
- Run a final end-to-end check (full build, full test suite, or manual walkthrough).
- Summarize what was done, what changed, and any remaining open items.
Practical Rules
- Plans are living documents -- update them as you learn more.
- Prefer many small steps over a few large ones.
- Each step should have a clear "done" condition.
- If the scope grows mid-execution, call it out and re-plan.
- Time-box exploratory steps to avoid rabbit holes.
Anti-patterns to Avoid
- Starting to code before having a plan.
- Writing a plan but then ignoring it.
- Making a single giant step that bundles multiple concerns.
- Silently changing course when stuck instead of communicating.
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 · 55 lines · 17 tokens per session scan A 55b729965ac4
plan-and-execute is a skill published in the GitHub repository 0xranx/agentbrief (45 stars, last pushed 5mo ago), licensed MIT. It adds 17 tokens to every session and 475 once invoked, about $0.0001 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
pptx
从论文、大纲或结构化文本生成 PowerPoint (.pptx) 演示文稿。Use when 用户需要把一篇论文/文章/大纲做成幻灯片、slides、演示文稿、PPT、deck。Don't use when 只需纯文本总结、生成 Word/PDF、或修改已有 pptx 的单个像素级样式。.
ai-style
当任务是用中文撰写或改写面向读者的文案（产品发布稿、公众号文章、邮件、README 等）， 或用户反馈文字「AI 味太重」「不像人写的」时，加载本 Skill。.
curly-quote-sft
Skill "curly-quote-sft" from bojieli/ai-agent-book, covering 中文技术文档符号与引用规范, 何时加载, 符号定义, 决策优先级 and 正反例约束.
triage
你是当前任务的分诊协调者。先识别用户的全部目标、顺序依赖和验收条件，再按 “事实检索 → 计算/执行 → 写作”顺序逐步请求切换到需要的专业能力。不要替专业 能力完成它的工作，也不要在信息缺失时臆造结果。.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
research
用真实检索工具查找可追溯的事实、数据和来源。.