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/ooooooooooooooooooop/agent-tools/clarify-before-changenpx skills add ooooooooooooooooooop/agent-tools --skill clarify-before-changegit clone --depth 1 https://github.com/ooooooooooooooooooop/agent-toolsWrote 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/ooooooooooooooooooop/agent-tools/clarify-before-change)<a href="https://agentmods.dev/skills/ooooooooooooooooooop/agent-tools/clarify-before-change"><img src="https://agentmods.dev/badge/skills/ooooooooooooooooooop/agent-tools/clarify-before-change.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 | $0.00075 | $0.00954 |
| Opus 5 | $0.00037 | $0.00477 |
| Sonnet 5 | $0.00015 | $0.00191 |
| Haiku 4.5 | $0.00007 | $0.00095 |
Grade A, and why
clarify-before-change 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
修改前澄清
适用范围
当修改目标、业务含义、影响范围或验收标准存在实质歧义时使用。本 Skill 只建立变更边界，不执行修改。
工作流程
- 用一句话重述用户目标。
- 先检查代码、配置、测试、规则、调用关系和历史行为，优先从仓库证据消除歧义。
- 列出仍然会影响目标、业务语义或不可逆范围的缺失信息。
- 明确默认假设、主要风险、受影响文件和可回滚方式。
- 给出最小可执行路径和验收标准。
- 只有缺失信息确实阻止继续时才提一个关键问题；否则采用可逆假设继续。
意图解析策略（Canonical）
本节是全部执行类 Skill 中"是否需要询问用户"的唯一权威语义。其他 Skill（unified-taskflow、task-mode-router、subagent-execution-governance 等）的询问/确认规则不得比本节更宽。
自主解析顺序（先自己解决）
缺失信息可按以下任一途径获得的，必须先自行获取，不得询问用户：
当前上下文 → Personal Memory / Project State → 仓库 / config / tests → 历史 trace / sessions → web / docs → 可逆实验。
可逆假设（记录即推进，不暂停）
存在多个合理选择，但同时满足：可逆、低成本、不改变用户目标、无重大外部后果 —— 选择最合理默认值，在决策记录中登记 assumption，继续执行。禁止暂停等待确认。
允许询问（穷尽后才问，一次问完）
只有答案会实质改变以下之一时才允许提问：objective / 业务语义 / 不可逆动作 / 隐私与安全暴露 / 有意义的成本 / 互斥价值偏好。确需提问时，最多一轮把真正必要的问题问完，禁止挤牙膏式反复澄清。
续接语义（"继续" = 已授权推进）
用户说"继续 / 做完 / 接着做 / 自主推进 / 按之前目标完成"，统一解释为：在当前 objective / critical constraints / non-goals 内，Agent 已获得继续选择下一步的授权。禁止：重新让用户选择计划、重新确认已知信息、重复询问是否继续、重新进行完整 Phase 0。先恢复 current state → 未闭合 done criteria → next best action，然后直接推进。
证据门禁
将请求分为：
audit：只读检查，不创建报告、不修改文件、不同步目的地。change：用户已授权的可逆修改，有明确目标和验证方式。high-risk：删除、移动、用户级/全局写入、凭据、权限或外部系统操作。
不要因为“可能存在不确定性”就停下；只有答案会改变目标、业务意义或不可逆范围时才提问。
决策记录
中型或大型修改在动手前记录：
事实：已由仓库证据确认的内容
假设：尚未确认但可逆的选择
风险：文件、行为、数据和外部状态影响
最小路径：满足目标的最小改动
非目标：明确不改的相邻内容
状态：proceed | ask | blocked
输出契约
审计或已完成的澄清应报告目标、证据、假设、风险、最小路径、非目标和状态。需要提问时最多提出一个会改变执行边界的问题。
验证
继续执行前确认：目标路径已确定、写入权限已获得、删除/移动目标已精确解析、验收条件可观察。相关示例见 ambiguous-restructure.md。
What ships with it
2 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.
- 4d ago First seen · 73 lines · 75 tokens per session scan A 79c0fd737d27
clarify-before-change is a skill published in the GitHub repository ooooooooooooooooooop/agent-tools (2 stars, last pushed 6d ago), licensed MIT. It adds 75 tokens to every session and 954 once invoked, about $0.0004 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
session-deep-dive
Deep qualitative analysis of high-signal sessions. Spawns subagents with v2 template, synthesizes patterns, compares against known findings. Use after /session-scan.
brainstorm
Brainstorm Elixir/Phoenix features — explore ideas, compare approaches, gather requirements. Use when vague idea, not sure how to approach, or want to discuss before plan.
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
plugin-dev-workflow
Guide plugin development workflow — editing skills, agents, hooks, or eval framework in this repo. Use when modifying files in plugins/elixir-phoenix/, lab/eval/, or lab/autoresearch/. Ensures changes pass eval, lint, and tests before committing.
elixir-idioms
OTP/BEAM patterns and Elixir idioms — GenServer, Supervisor, Task, Registry, pattern matching, with chains, pipes. Use when designing processes or debugging BEAM issues.
security
Enforce Elixir/Phoenix security — auth, OAuth, sessions, CSRF, XSS, SQL injection, input validation, secrets. Use when editing auth files, login flows, RBAC, or API keys.