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/ooooooooooooooooooop/agent-tools/unified-taskflownpx skills add ooooooooooooooooooop/agent-tools --skill unified-taskflowgit clone --depth 1 https://github.com/ooooooooooooooooooop/agent-toolsWrote 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/ooooooooooooooooooop/agent-tools/unified-taskflow)<a href="https://agentmods.dev/skills/ooooooooooooooooooop/agent-tools/unified-taskflow"><img src="https://agentmods.dev/badge/skills/ooooooooooooooooooop/agent-tools/unified-taskflow.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 | $0.00104 | $0.03128 |
| Opus 5 | $0.00052 | $0.01564 |
| Sonnet 5 | $0.00021 | $0.00626 |
| Haiku 4.5 | $0.00010 | $0.00313 |
Grade A, and why
unified-taskflow 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 3d 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 — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Unified Taskflow v4.3
更新：2026-08-10
[!CAUTION] 核心规则
- 只有通过触发门禁后，才启动 unified-taskflow；不要把普通任务流程化
- 启动后，任务管理使用项目根目录下的
.taskflow/目录，不使用内置 artifact 目录- 禁止跨阶段推理 — 执行时不能跳回规划，规划时不能偷跑代码
- 如不确定是否需要启动，先用
task-mode-router判断；仍不确定时询问用户，不默认触发
规则优先级（冲突时按此顺序裁决）： Safety > Correctness > Efficiency > Completeness
执行语义优先级（与执行类 Skill 冲突时按此裁决，详见 execution-discipline「自主执行契约」）： Safety/不可逆授权 > 用户显式目标与约束 > 合法停止策略 > 自主续接 > 流程便利。 本 skill 的任何流程规则不得覆盖
clarify-before-change的更窄询问边界，也不得覆盖execution-discipline的停止/恢复语义。
触发判断
触发：
- 用户明确说“使用 unified-taskflow / taskflow / .taskflow”。
- 任务跨多轮、多文件、多阶段，且需要可恢复的执行记录。
- 任务需要明确的 anchor、checkpoint、design、验收标准和回滚路径。
- 用户要求长期复盘、审计轨迹、阶段冻结或复杂交接。
不触发：
- 简单问答、单行修改、单文件小修。
- 普通 skill description 小改、文案调整、同步用户级 skill。
- 普通“优化 / 完善 / 重构 / 更稳定”，除非用户明确要求重型流程。
clarify-before-change、task-mode-router、minimal-implementation已足够控制风险的任务。
路由关系：
- 先由
task-mode-router判断任务模式。 - 小任务和中等任务默认不用
.taskflow/。 - 只有大型、长任务、可审计交接任务才进入本 skill。
- 进入本 skill 后，仍遵守
minimal-implementation，不为了流程完整性扩大实现范围。
按需加载
- 进入 Phase 0 → 读取 phase0-clarification.md
- 需要交互决策 → 读取 interaction-design.md
- 治理规则细节 → 读取 governance.md
- Re-grounding 细节 → 读取 regrounding-protocol.md
工作流
Phase 0: 理解快照（Understanding Snapshot）
目的：确保 Agent 正确理解用户需求，生成防幻觉锚点。
- 确认已通过触发门禁；未通过时退回普通任务流程
- 禁止立即创建文档或代码
- Agent 输出理解快照：
- 用户意图（一句话）
- 识别到的歧义点
- Agent 的假设（显式列出并标注可逆性：可逆假设记录即推进；仅目标级/不可逆假设需用户确认）
- 默认直接进入完备性门禁并写入 anchor.md；仅当存在目标级/不可逆假设或意图级歧义时才请求用户确认（询问边界以
clarify-before-change意图解析策略为准，一次问完） - 完备性门禁（详见 phase0-clarification.md）
- 写入
anchor.md（北极星文件，含版本号）
问题框架（参考，不强制全部使用）：边界 / 约束 / 优先级 / 风险 详见 phase0-clarification.md
执行（Elastic Execution）
弹性深度 — 根据任务复杂度自然展开，无固定档位：
- 重型任务最小路径：anchor.md → checkpoint.md → 执行 → 验收核对
- 需要设计时：anchor.md → design.md → checkpoint.md → 执行 → 验收核对
- 不做：为低风险小任务创建
.taskflow/、anchor、checkpoint 或 design
What ships with it
11 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.
- agents/openai.yaml 279 B
- assets/templates/anchor.md 879 B
- assets/templates/checkpoint.md 1.6 KB
- assets/templates/design.md 593 B
- examples/refactor-order-module.md 1.9 KB
- references/governance.md 5.3 KB
- references/interaction-design.md 1.2 KB
- references/phase0-clarification.md 3.8 KB
- references/regrounding-protocol.md 4.8 KB
- scripts/session-catchup.py 6.1 KB runs code
- scripts/task-lifecycle.py 28 KB runs code
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.
- 3d ago First seen · 208 lines · 104 tokens per session scan A 240455eec23b
unified-taskflow is a skill published in the GitHub repository ooooooooooooooooooop/agent-tools (2 stars, last pushed 5d ago), licensed MIT. It adds 104 tokens to every session and 3,128 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
zlog
Multi-agent session log compressor and storage optimizer. Compresses .log, .out, .txt, .trace (>10KB) to .zst, .xz, or .gz (saving 77%-99.9% disk space) across /.gemini, /.config/Cursor, /.ollama, /.claude, /.windsurf, /.codex, etc. Auto-discovers AI log dirs, purges empty 0-byte logs. Safe for concurrent…
amazon-reviews-api-skill
This skill helps users automatically extract Amazon product reviews via the Amazon Reviews API. Agent should proactively apply this skill when users express needs like getting reviews for Amazon product with ASIN B07TS6R1SF, analyzing customer feedback for a specific Amazon item, getting ratings and comments for a…
amazon-competitor-analyzer
Scrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive analysis. Compares specifications, pricing, review quality, and visual strategies to identify competitor moats and vulnerabilities.
muapi-media-editing
Edit and enhance images and videos with AI via muapi.ai — prompt-based editing, upscaling, background removal, face swap, lipsync, video effects, and more.
ctf-malware
Provides malware analysis and network traffic techniques for CTF challenges. Use when analyzing obfuscated scripts, malicious packages, custom crypto protocols, C2 traffic, PE/.NET binaries, RC4/AES encrypted communications, YARA rules, shellcode analysis, memory forensics for malware (Volatility malfind, process…
research
Conduct preliminary research on a topic and generate research outline. For academic research, benchmark research, technology selection, etc.