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 pieable/dragon-ball-agent --skill workflow-state-distillergit clone --depth 1 https://github.com/pieable/dragon-ball-agentWrote 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/pieable/dragon-ball-agent/workflow-state-distiller)<a href="https://agentmods.dev/skills/pieable/dragon-ball-agent/workflow-state-distiller"><img src="https://agentmods.dev/badge/skills/pieable/dragon-ball-agent/workflow-state-distiller.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00101 | $0.03190 |
| Opus 5 | $0.00051 | $0.01595 |
| Sonnet 5 | $0.00020 | $0.00638 |
| Haiku 4.5 | $0.00010 | $0.00319 |
Grade A, and why
workflow-state-distiller 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow State Distiller
目标
从用户明确说过的话、实际选择、纠正和试用结果中,逐步弄清当前任务要做到什么、结果拿来做什么、哪些代价不能接受,以及用户希望怎样协作。
用户无需在项目开始时一次说清完整规格。从已经明确的部分开始,把当前理解作为可修正状态。新证据出现时更新、缩小、拆分或撤回旧理解。
成功意味着 Codex 下一步做得更接近用户的实际需要,几条相关反馈被合并成更少、更清楚的要求,而且能看出哪些是用户明确说的、哪些是暂时推测的、哪些还没有确定。
当前任务里的反馈先只用于当前任务。只有用户明确确认,或者多个项目中的实际选择都支持同一要求时,才把它当成跨项目原则。
加载后的范围判断
先判断是否需要完整重建任务状态。若继续行动可能因为零散或失效的理解而遗漏有效要求、误判适用范围或改变下一步,就执行本 Skill。若目的、边界和下一步仍然稳定,就按原任务继续,不因信息很多、执行错误、普通返工或等待外部状态而机械蒸馏。
需要完整重建时,先暂停依赖旧理解继续扩写规则或大幅重做成果。不要只总结用户最新一句话,而要恢复目的、背景、行动、结果、边界及仍未证实的原因解释之间的当前关系,形成足以解释保留、否定和变化的最小整体理解后,再继续行动。
维护的任务状态
只维护会改变行动的五类内容:
- 目的:为什么做、最终要保护什么,以及发生取舍时优先什么。
- 背景:交付对象、使用场景、关键来源、实际选择、实验结果和仍影响判断的失败路线。
- 行动:Codex 当前要做什么,以及确实会改变结果的协作方式、方法或顺序。
- 结果:交付物、受众、完成状态、详细程度和使用方式。
- 边界:必须保持不变的事项、权限范围、不可接受的代价和需要确认的决定。
这些内容可以暂时不完整。提问是形成和修正理解的正常方式。答案可能改变目标、结果、边界、重要路线或高成本行动时,优先把相应问题问清。能够从任务对象查明的信息主动调查,不依赖回答的工作可以继续推进。记录一项理解时,同时记清它来自哪里、只适用于什么情境,以及什么新证据会让它失效。
回看历史时,只看可能改变当前决定的材料。已经不影响行动的旧对话和调试过程留在原始记录里。
四类证据必须分开:
- 直接证据:用户的选择、保留、否定、实际使用感受和已经发生的结果。
- 明确决定:用户直接确认的目标、限制、权限和取舍。
- 原因假设:用户或模型对“为什么”的解释,分别标明来源。
- 未形成偏好:现在没有答案,需要通过比较或试用形成。
用户的直接感受可以确定“结果不符合需要”,但不能单独证明原因。明确提出的原因仍先作为原因假设,除非有独立证据或后续选择支持。
这些理解有多确定
根据证据强度区分:
- 明确事实:用户直接说明的目标、决定或限制。
- 局部修正:只对当前内容、版本、场景或动作生效。
- 工作假设:目前最合理、可以指导低风险行动,但以后可能改掉的理解。
- 候选原则:几个不同情境都支持,但适用范围或例外还不够清楚。
- 已确认原则:用户明确认可,或者已有稳定证据、清楚范围,并且能正确判断相似场景中的选择。
- 硬边界:用户明确要求不能越过,或涉及安全、权限和不可逆影响的限制。
工作假设和候选原则只用于它们有证据支持的范围。长期资料只记录已确认原则和硬边界。
一项理解是否升级为原则,要看它有没有不同来源的证据、范围是否清楚,以及它能不能正确解释相似场景中的选择,不能只数出现了几次。新证据也可以缩小、替换或取消已经确认的原则。用户明确提出的硬边界立即生效,不需要反复证明。
要求写多重
规则的措辞要和证据强弱相称:
- 局部修正写成“这次……”。
- 工作假设写成“目前先按……处理”。
- 候选原则写成“在这类情境中通常……”或“优先……”。
- 已确认原则写成清楚的默认要求。
- “必须”“不得”“绝不”“任何时候都”等最强措辞只用于用户明确要求的硬边界,或安全、权限和不可逆风险。
正向要求也可能写得过强。证据只支持“优先简洁”时,就保持“优先”,不要改成“所有回答必须极短”。
蒸馏流程
1. 先弄清反馈发生在哪
确定当时的任务、交付对象、Codex 的行动、用户实际否定或保留的内容,以及反馈改变的是结果、用途、取舍、合作方式还是局部细节。
2. 把事实和推测分开
先记用户原意、实际选择、试用结果和已经发生的事实,再说明 Codex 怎样理解。说明这项理解只适用于哪里,并允许后续证据改掉它。
3. 用下一步行动检验理解
先保留足以决定下一步的理解:用户想要什么结果、不接受什么代价、这项取舍适用于哪里。然后逐项删除。如果删除某项后,目标、输出、提问、权限、风险处理和下一步行动都不变,该项不进入当前状态。有多个解释时,只保留会导向不同重要行动的解释。导向同一安全行动的差异不需要记录。
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 · 180 lines · 101 tokens per session scan A 364687e8e585
workflow-state-distiller is a skill published in the GitHub repository pieable/dragon-ball-agent (11 stars, last pushed 6d ago), licensed MIT. It adds 101 tokens to every session and 3,190 once invoked, about $0.0005 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…