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/ryanzhao1011/workframe/task-managementnpx skills add ryanzhao1011/workframe --skill task-managementgit clone --depth 1 https://github.com/ryanzhao1011/workframeWhat 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 | $0.00020 | $0.03550 |
| Opus 5 | $0.00010 | $0.01775 |
| Sonnet 5 | $0.00004 | $0.00710 |
| Haiku 4.5 | $0.00002 | $0.00355 |
Grade B, and why
task-management scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
python "$(cat .claude/workframe-state/plugin-root.txt)/bin/workframe-recompute-board-summary" How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
任务管理技能
board.yaml 格式规范
# projects/board.yaml
summary:
total: 0
pending: 0
in_progress: 0
pending_qa: 0
completed: 0
blocked: 0
cancelled: 0
last_updated: "YYYY-MM-DD"
tasks:
- id: "TASK-001"
title: "任务标题"
description: "任务描述"
status: pending # pending | in_progress | pending_qa | completed | blocked | cancelled
priority: P1 # P0 | P1 | P2
assigned_to: dev # pm | dev | qa | prompt-eng
created_at: "YYYY-MM-DD"
updated_at: "YYYY-MM-DD"
deadline: null # "YYYY-MM-DD" 可选；有截止要求才填。heartbeat-check.py 会扫此字段判逾期
depends_on: [] # 依赖的任务 ID 列表
tags: [] # 标签（合法值见下方约定）
estimate_hours: 4 # 预估工时（小时）
notes: "" # 备注
# ── modules/ 体系叠加字段 ──
# module: profile/edit # ★ 二段式 basic/sub；modules/ 体系下必填
# req_slug: avatar-cropper # 可选；需求级任务用，对应 modules/<basic>/<sub>/requirements/<req_slug>/
# sub_req_slug: main # 与 req_slug 同进同出；main 也要显式写
# # （缺省按 main 解释仅对**存量**条目成立）
# affected_modules: [] # 可选；横切多模块任务用二段式数组
# ── 可选生命周期字段（按事件触发写入）─────────────────────
# completed_at: "YYYY-MM-DD" # status 改为 completed 时填写
# actual_output: "" # completed 时补充实际产出描述
# blocked_reason: "" # status 改为 blocked 时必填
# cancelled_at: "YYYY-MM-DD" # status 改为 cancelled 时填写
# cancel_reason: "" # cancelled 时必填
modules/ 体系字段
modules/ 体系下，task 字段叠加 modules 归属：
| 字段 | 取值 | 必填条件 |
|---|---|---|
module |
二段式 <basic>/<sub>，如 profile/edit |
modules/ 体系下必填（与 issue 字段策略一致） |
req_slug |
父需求 slug，如 avatar-cropper |
需求级任务必填（document-norms §2.6 引用契约）；维护 / 看板 / 记忆整理这类不挂需求的任务留空 |
sub_req_slug |
子需求 slug，如 main 或 phase-1 |
与 req_slug 同进同出——填了 req_slug 就必须填它（main 也显式写）。只有存量条目缺它时才按 main 解释，那是兼容条款不是写法（document-norms §2.6） |
affected_modules |
二段式数组 [a/b, c/d] |
横切多模块任务可选 |
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 First seen · 199 lines · 20 tokens per session scan B 00e8440dbba4
task-management is a skill published in the GitHub repository ryanzhao1011/workframe (4 stars, last pushed 15d ago), licensed MIT. It adds 20 tokens to every session and 3,550 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
acceptance-orchestrator
Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention.
agent-project-board-sync
Agent skill for project-board-sync - invoke with $agent-project-board-sync.
openspec-archive-change
Archive a completed change in the experimental workflow. Use when the user wants to finalize and archive a change after implementation is complete.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
goal-loop
Bootstrap a goal-driven self-improving AutoNudge loop. Give it a goal + anchor directory; it generates LOOP.md + GOAL.md + kanban board, then you write the Definition of Done and arm the loop. The running agent manages the board autonomously: finds issues, adds cards, resolves them, handoffs to Review, repeats until…
directory-management
Manages project directory setup and artifact organization. Use when starting a new project, resuming an existing one, or when a PLAN.md needs to be associated with a project directory. Creates the project folder structure (specs/, scripts/, notebooks/, manifests/, agentmemory/) and resolves project naming.