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/fitlab-ai/agent-infra/block-tasknpx skills add fitlab-ai/agent-infra --skill block-taskgit 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/block-task)<a href="https://agentmods.dev/skills/fitlab-ai/agent-infra/block-task"><img src="https://agentmods.dev/badge/skills/fitlab-ai/agent-infra/block-task.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 5.1 | $0.00052 | $0.01866 |
| Opus 5 | $0.00026 | $0.00933 |
| Sonnet 5 | $0.00010 | $0.00373 |
| Haiku 4.5 | $0.00005 | $0.00187 |
Grade A, and why
block-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 2d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
标记任务阻塞
--agent取值见.agents/rules/task-management.md「合作者 token 规范」。
行为边界 / 关键规则
- 本命令更新任务元数据并物理移动任务目录
- 仅在确实无法继续时才阻塞 —— 如果是可以克服的困难,先尝试解决
使用场景
- 技术问题:无法解决的 Bug、缺少依赖、基础设施问题
- 需求问题:需求不明确、规格冲突、待定决策
- 资源问题:缺少访问权限、等待外部团队、被其他任务阻塞
- 需要决策:待定的架构决策、需要利益相关者批准
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。
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:本地生命周期边界
确认前置条件后,由步骤 3 的单次 lifecycle intent 原子写入 started/done 日志、基础元数据、目录转移和短号释放;本步骤不得提前手工写入其中任一项。
执行步骤
1. 验证任务存在
检查任务是否存在于 .agents/workspace/active/{task-id}/。
注意:{task-id} 格式为 TASK-{yyyyMMdd-HHmmss},例如 TASK-20260306-143022
如果未找到,检查其他目录并告知用户。
2. 分析阻塞原因
阻塞之前,彻底分析:
- 具体的问题是什么?
- 根本原因是什么?
- 已经尝试了哪些解决方案?
- 需要什么帮助或信息才能解除阻塞?
3. 执行本地生命周期意图
agent-infra-internal task-lifecycle {task-id} block --agent {standard-agent-token} \
--reason "{一行原因}" --unblock-condition "{解除阻塞条件}"
解析 stdout 单 JSON。仅 status=applied|no-op 视为本地完成;status=failed 时展示 error 与 completedSteps/pendingSteps,不得宣称任务已阻塞。生命周期核心统一维护 status/blocked_at、阻塞信息、Activity Log、目录与短号。
4. 验证本地终态
确认结构化结果的 targetState=blocked、目标路径为 .agents/workspace/blocked/{task-id}、短号效果已提交,并检查:
ls .agents/workspace/blocked/{task-id}/task.md
5. 保留恢复身份
记录 lifecycle 结果中的请求身份与规范 metadata,供失败后以同一 intent 安全重试;不得手工补写局部状态。
6. 同步到 Issue(可选)
检查 task.md 中是否存在有效的 issue_number。如果没有,跳过。
如果存在有效的 issue_number,调用 agent-infra-internal platform-issue sync {task-id} --agent {standard-agent-token} --status blocked。
随后调用 agent-infra-internal platform-comment sync {task-id} --kind task --agent {standard-agent-token} 更新 task 评论。
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.
- 2d ago Changed 2ba4c58e412c
- 6d ago First seen · 158 lines · 52 tokens per session scan A 8da1d4ce5728
block-task is a skill published in the GitHub repository fitlab-ai/agent-infra (83 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 1,866 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
contextualize
Detect application-context mismatch after execution. Fires when correct output may not fit the actual context. Type: (ApplicationDecontextualized, AI, CONTEXTUALIZE, Result) → ContextualizedExecution.
review-loop
Convergence-paced review-resolve loop over a change and its governing surfaces. Verifies each finding against the codebase and the base it is measured from, then re-reviews until each is disposed of.
conduct
Conduct method before object-level work. Fires when the work needs several moves in non-trivial order. Type: (MethodUnderdetermined, Hybrid, CONDUCT, WorkProspect × MoveGround) → ConductedMethod.
apportion
Apportion an autonomous goal into execution units carrying their own completion conditions. Type: (GoalPlanUncompiled, User, APPORTION, AutonomousGoal × ExecutionHorizon) → ConditionBearingUnitPlan.
ground
Validate structural mapping between abstract and concrete domains. Presents concrete instantiations when mapping uncertainty is detected. Type: (MappingUncertain, AI, GROUND, R) → ValidatedMapping.
steer
Project-profile recalibration. Audits session calibration drift, presents per-cluster evidence for a user verdict, writes the updated project-profile rule, and inscribes a settled-direction clause.