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/code-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/code-task)<a href="https://agentmods.dev/skills/fitlab-ai/agent-infra/code-task"><img src="https://agentmods.dev/badge/skills/fitlab-ai/agent-infra/code-task/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/fitlab-ai/agent-infra/code-task"><img src="https://agentmods.dev/badge/skills/fitlab-ai/agent-infra/code-task.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00056 | $0.05140 |
| Opus 5.5 | $0.00022 | $0.02056 |
| Sonnet 5.5 | $0.00011 | $0.01028 |
| Haiku 4.5 | $0.00006 | $0.00514 |
Grade A, and why
code-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 — 270 lines — stays where its author put it; the contents beside it link to each section on GitHub.
编码任务
--agent取值见.agents/rules/task-management.md「合作者 token 规范」。
生命周期事件必须携带显式触发信息：普通技能调用使用 model；仅用户明确要求时使用 human。{request-id} 是本任务与本轮产物的稳定单行标识，{reason-code} 初次实现使用 user-request，修复或裁决使用 review-finding；started 与 completed 使用同一组值。
根据所选生命周期路径的实现输入编码任务，并产出 code.md 或 code-r{N}.md。本技能支持初次实现、基于 review-code 反馈的修复，以及人工裁决驱动实现三种模式。
行为边界 / 关键规则
路径与返工
本阶段只消费核心从最新有效分析产物解析出的规范路径事实；未被所选路径包含的阶段不得创建产物。同阶段完成一次修订—复审后再次收到 Changes Requested 时，必须在下一执行产物前提交绑定 finding、来源 SHA 和稳定任务事实摘要的返工分类；轮次或文件名变化不是新证据。
持久化报告证据
生成实现报告时，先读取 .agents/rules/evidence-reporting.md。成功测试记录命令、目标范围、状态/结构化结果、实际结果和未覆盖部分；失败、阻塞或争议保留复现入口、准确位置和决定性摘录，不默认粘贴完整成功 stdout。
- 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，并在实现报告记录三张资格审计决策表和资格快照；不得把来源不明或未确认约束自动升级为排除条件 - 严格遵循核心选择的最新生命周期输入：精简路径为
analysis.md/analysis-r{N}.md，标准或完整路径为plan.md/plan-r{N}.md - 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 - 实现前读取
.agents/rules/compatibility-policy.md；只实现方案明确批准的兼容预算，不以“稳妥”为由保留旧分支、旧结果契约或迁移 shim - 修复模式逐条核实最新
review-code的发现：成立则修复，判定为不成立/幻觉则在报告中反驳并记入 unresolved；不擅自扩大到审查未列出的问题；manual-validation 项不在修复范围 - 实现报告写完后，必须先通过
task-artifact ... preflight --family code，再写入待处理账本、创建 checkpoint、执行后续 Issue 同步或发布code.completed。preflight 只验证并封存 generation，不发布 formal/task/ledger/platform 状态；checkpoint 后运行finalize-local重新验证并取得摘要，code.completed事件登记该摘要。 - 实现中遇到方案未覆盖的关键设计决策时，调用
agent-infra-internal task-ledger {task-id} decision-next-id取得HD-N，按.agents/rules/human-decision-context.md将详情写入实现报告的## 人工裁决待办并判断是否需要实现；把decision-upsert --id {HD-N} --stage code --artifact {code-artifact} --needs-implementation {true|false}留作待处理账本更新，在报告 preflight 通过后再执行。不得扫描编号、手写账本行、中途提问或擅自扩范围。 - 完成本技能必须创建一个本地 checkpoint：实现报告 preflight 通过后直接调用共享 commit core，使用
delivery: { mode: 'local' }。不调用独立commit技能、不运行原始git add/git commit，也不推送远端。checkpoint 使用 durable intent；只有 checkpoint 与 task 状态同步成功后才发送code.completed - 每轮实现都创建新的实现产物，不覆盖旧文件
- 执行本技能后，你必须立即更新 task.md
What ships with it
7 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.
- today Changed fb9593a2d2f4
- 6d ago Changed 1a0bb4376f32
- 23d ago Changed c0d50860e90d
- 24d ago Changed 152fbe68f3a3
- 26d ago Changed · +17 lines 21e63ce4a037
- 28d ago Changed e191275843c8
- 29d ago Changed 491923d87125
- 1mo ago Changed 674edd784d8a
- 1mo ago Changed · +2 lines 39119ae24cef
- 1mo ago First seen · 251 lines · 56 tokens per session scan A 53cebf4a1d1b
code-task is a skill published in the GitHub repository fitlab-ai/agent-infra (86 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 5,140 once invoked, about $0.0002 per session on Opus 5.5. 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
plan-tree
Maintain a structured planning document tree made of roadmap/status files, implementation status or handoff TODO files, topic notes, decision records, open questions, ideas/inspiration pools, and repository/file-structure hygiene plans. Use when Codex needs to create, reorganize, audit, or update a multi-file plan…
ccb-github
Maintain this CCB project's GitHub-facing release and npm publication surface. Use when preparing, publishing, auditing, or fixing CCB releases; updating README.md, README/zh.md, localized README files, CHANGELOG.md, VERSION, package.json, GitHub release notes/assets, repository description/topics, npm registry state…
planner-task-packet
Draft CCB workflow task packets, readiness recommendations, and candidate clarification questions without mutating authoritative state.
orchestration-bundle-candidate
Select one route and return one adaptive one-to-four-workgroup bundle candidate as reply-only evidence.
planner-closure-backfill
Produce one revision-fenced Planner backfill proposal for either a Detailer replan or task-set closure, with compact Frontdesk status evidence.
ccb-diagnose
Diagnose a named CCB agent by combining authoritative runtime and job lineage with deep read-only pane inspection, apply bounded recovery when evidence supports it, verify the result, and request authorization before submitting a redacted GitHub issue. Use for $ccbdiagnose agentname, $ccb-diagnose agentname, or…