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/kanocifer/devtaskmcp/devtasknpx skills add KanoCifer/DevTaskMcp --skill devtaskgit clone --depth 1 https://github.com/KanoCifer/DevTaskMcpWhat 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 | $0.00104 | $0.01263 |
| Opus 5 | $0.00052 | $0.00632 |
| Sonnet 5 | $0.00021 | $0.00253 |
| Haiku 4.5 | $0.00010 | $0.00126 |
Grade A, and why
devtask 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 yesterday.
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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
devtask
把需求或 bug 变成落库的可执行 task。遵循 ../references/task-contract.md 的 Task Document 契约。
模式选择
探索后按规模路由：
单点改动，问题已定义（≤5 文件） → Lightweight（方案 → 落库一个 task）
3+ 独立诉求 → Triage（分类 → accepted 批量落库）
价值/存在判断 → Evaluation（Keep / Kill / Pivot）
多文件、多层次、需拆解（>5 文件）→ Spec + Subtasks（含 Grilling）
只想探讨方案，不立即落库 → Grilling（references/grill.md）
拿不准 → 默认 Lightweight；探索完发现复杂再升 Spec
流程
1. 探索
- 模块名 → codegraph_explore / Read / grep
- bug → 搜索 error path / 最近改动；"接 XXX 功能" → 找对应 endpoint / handler / service
- 涉及框架能力时优先查官方方案
退出条件： 知道改哪些文件、怎么改、影响范围。能从代码查到的事实不问。
2a. Lightweight — 单点改动
列出文件路径 + 每文件改动概要。推荐方案默认采用。3+ 种真正不同路径时让用户选。
→ 直接落库：
create_task(
title="...",
task_type="问题", # 问题 / 功能需求 / 优化 / 技术债
priority="P2 中",
scope="Backend-Python",
detail="## Goal\n...\n\n## Acceptance Criteria\n- [ ] ..."
)
完成后只回报 slug。
2b. Triage — 批量杂项
每项分 Bug / Already works / Accepted / Cosmetic / Out of scope。展示分类表确认 → Accepted 各项逐个调 create_task(...) 创建。不要合并成一个 task。
2c. Evaluation — 存在判断
输出 Keep / Kill / Pivot（第一行结论，不要开场白，三条理由）。Kill 不落库；Pivot 落库新方向；Keep 落库 task。
2d. Spec + Subtasks — 复杂需求
Grilling： 按 references/grill.md 的 frontier 访谈协议执行：每轮同时询问当前 frontier 的所有决策，给出推荐答案；等待用户回答后再扩展下一轮。顺序：方案选型 → 关键决策 → 实现步骤 → 验收条件 → 脆弱假设 → 约束红线。提问必须具体到另一个工程师可以据此实现。
落库 spec：
create_task(
title="<spec 标题>",
task_type="功能需求", # 或 优化 / 问题 / 技术债
priority="P1 高",
scope="Backend-Python",
kind="spec",
detail="## Goal\n...\n\n## Plan\n...\n\n## Acceptance Criteria\n- [ ] ..."
)
记下返回的 slug。
逐个创建 subtask：
create_task(
title="<子任务标题>",
task_type="功能需求",
priority="P1 高",
scope="Backend-Python",
kind="subtask",
parent_slug="<spec-slug>", # spec 返回的 slug
blocked_by=["task-N1"], # 同层依赖（可选）
detail="## Goal\n..." # 只放增量内容，重复的不抄父
)
交付：
Spec: task-N (kind: spec)
├── task-N1: <title> [parent: task-N]
├── task-N2: <title> [parent: task-N]
└── task-N3: <title> [parent: task-N]
Approved? 启动：devtask-doit task-N1
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.
- yesterday First seen · 118 lines · 104 tokens per session scan A 1c01c836e0c6
devtask is a skill published in the GitHub repository KanoCifer/DevTaskMcp (0 stars, last pushed 7d ago), licensed MIT. It adds 104 tokens to every session and 1,263 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
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
setup-matt-pocock-skills
Configure this repo for the engineering skills: set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
retro
Facilitate a structured sprint retrospective — what went well, what didn't, and prioritized action items with owners and deadlines. Use when running a retrospective, reflecting on a sprint, creating action items from team feedback, or learning how to run effective retros.
bug-triage
Read all open bugs in production/qa/bugs/, re-evaluate priority vs. severity, assign to sprints, surface systemic trends, and produce a triage report. Run at sprint start or when the bug count grows enough to need re-prioritization.