Borrowing it
Nothing to install: this file belongs to fitlab-ai/agent-infra. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/fitlab-ai/agent-infra/main/.agents/skills/analyze-task/SKILL.mdgit clone --depth 1 https://github.com/fitlab-ai/agent-infraWrote 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/fitlab-ai/agent-infra/analyze-task)<a href="https://agentmods.dev/skills/fitlab-ai/agent-infra/analyze-task"><img src="https://agentmods.dev/badge/skills/fitlab-ai/agent-infra/analyze-task.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 | $0.00054 | $0.05103 |
| Opus 5 | $0.00027 | $0.02551 |
| Sonnet 5 | $0.00011 | $0.01021 |
| Haiku 4.5 | $0.00005 | $0.00510 |
Grade A, and why
analyze-task 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 today.
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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
分析任务
--agent取值见.agents/rules/task-management.md「合作者 token 规范」。
若入口业务操作数包含 --orchestrated，绑定 {execution-flag} = --orchestrated 并原样转发给 completed 事件；否则绑定为空。不得从 orchestration.json、环境变量或历史产物推断该标记。生命周期事件还必须携带显式触发信息：编排调用使用 {trigger-initiator}=orchestrator，否则使用 model；{request-id} 是本任务与本轮产物的稳定单行标识，{reason-code} 使用 user-request、new-requirement 或 upstream-fact-doubt；started 与 completed 使用同一组值。
行为边界 / 关键规则
持久化报告证据
生成分析报告时，先读取 .agents/rules/evidence-reporting.md。状态核对和成功检查记录命令、目标范围、状态/结构化结果、实际结果和未覆盖部分；失败、阻塞或争议才附决定性原文摘录。
- 涉及候选资格或
HD-N判断时，先读取.agents/rules/decision-qualification.md，基于 task.md 规范化约束/候选完成资格审计，并在分析产物记录五张资格审计表；不得把来源不明或未确认约束自动升级为排除条件 - 本技能仅产出需求分析文档（
analysis.md或analysis-r{N}.md）—— 不修改任何业务代码 - 严格基于
task.md中已有的任务输入、需求、上下文和来源信息展开分析 - 生成会同步到 Issue 的任务或生命周期 Markdown 前，先读取
.agents/rules/sync-content-generation.md并遵循其中的生成端约束；同步端不解析或改写正文 - 涉及旧行为、旧数据、旧 schema 或旧调用方时，先读取
.agents/rules/compatibility-policy.md；没有兼容准入证据时明确采用 current-only，不把推测写成需求 - 执行本技能后，你必须立即更新 task.md 中的任务状态
版本戳规则：创建或更新 task.md frontmatter 时，先读取 .agents/rules/version-stamp.md，并写入或刷新 agent_infra_version。
第 0 步：状态核对（执行前硬约束）
在加载 workflow / skill / rules 指令之后、做任何任务状态判断或用户可见结论之前，必须先执行状态核对。指令类文件读取不算对外动作或结论。
运行以下命令，并在本轮产物的 ## 状态核对 段记录任务/产物范围、关键结果和未覆盖部分；正常成功不粘贴完整目录清单或 task.md 尾部。失败、阻塞、身份不一致或争议时，附决定性原文行：
agent-infra-internal task-snapshot {task-id} --format text
状态核对完成前，禁止任何关于外部状态的断言（例如“代码没变”“测试已通过”“没有其他引用”），包括思考阶段。本门禁只提供结构下限；逐条证据配对和真实性仍需按报告模板与审查要求核对。
任务上下文解析
入口可省略 task ref；显式 task scope 仅接受
--task <ref>或-t <ref>，不再解释位置 task ref。保留其余业务操作数后调用agent-infra-internal task-context resolve {task-scope}；{task-scope}为空或 task flag 之一。只读取结构化结果的taskId，后续把{task-id}绑定为完整TASK-YYYYMMDD-HHMMSS。解析失败时透传非零退出码，不自行扫描任务。
解析任务引用，并确认任务位于本技能支持的状态或目录且存在
task.md；无法定位时按未找到任务处理并停止。
步骤开始：声明 started 事件
确认前置条件和轮次后、本轮第一个产出动作之前执行：
agent-infra-internal task-event {task-id} analyze.started --agent {standard-agent-token} --initiator {trigger-initiator} --request-id {request-id} --reason-code {reason-code}
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.
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.
- today Changed · +8 lines ae96da542502
- yesterday Changed · +9 lines d3cb3445700e
- 2d ago Changed 18315492f510
- 4d ago Changed · +8 lines 702bdb74a878
- 8d ago First seen · 281 lines · 54 tokens per session scan A 058aa0139ad3
analyze-task is a skill published in the GitHub repository fitlab-ai/agent-infra (83 stars, last pushed today), licensed MIT. It adds 54 tokens to every session and 5,103 once invoked, about $0.0003 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
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
preview-design
Render a real artifact through this branch's local MERIDIAN design code (not the published npm package) so the team can test the new Design Convention on the document / handoff / platform surfaces before it ships. Use for /preview-design, "preview the design convention", "render this with the new design", or Design…
sw-do
Implement a SpecWeave increment task by task through the ledger, with evidence per task and a verified close. Use for "implement this", "start working", "continue the increment", "keep going".
done
Close an increment: ledger check, specweave verify, optional review, then specweave complete. Use when all tasks are done and saying "close increment", "we are done", or "finish up".
pulp-cinema-director
Higgsfield Supercomputer skill for original pulp-cinema video direction: nonlinear crime scenes, standoffs, trunk-level shots, grindhouse, kung-fu homage, spaghetti-western energy, neon diners, chapter structure, and dialogue-heavy cinematic prompts.