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 skills add paceaitian/paceflow --skill pace-workflowgit clone --depth 1 https://github.com/paceaitian/paceflowWrote 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/paceaitian/paceflow/pace-workflow)<a href="https://agentmods.dev/skills/paceaitian/paceflow/pace-workflow"><img src="https://agentmods.dev/badge/skills/paceaitian/paceflow/pace-workflow/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/paceaitian/paceflow/pace-workflow"><img src="https://agentmods.dev/badge/skills/paceaitian/paceflow/pace-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Prompt Injection · line 160 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 160 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 233 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- high Prompt Injection · line 233 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Excessive Agency · line 90 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00035 | $0.07465 |
| Opus 5.5 | $0.00014 | $0.02986 |
| Sonnet 5.5 | $0.00007 | $0.01493 |
| Haiku 4.5 | $0.00003 | $0.00747 |
Grade A, and why
pace-workflow 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 1mo 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 — 279 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PACE 协议工作流程
artifact 由 artifact-writer agent 创建和维护。主 session 负责分析、执行代码、验证和向用户确认；artifact 写入动作统一派 agent。
本 skill 的定位：PACEflow 已启用后的流程引导（P-A-C-E-V-R）。要不要启用 PACE 不由本 skill 判断，而是 hook 在 SessionStart 确定性处理：强信号（有
changes/artifact /.pace-enabled/ artifact-root 配置）→ 自动门控；软信号（detectSoftSignal：3+ 代码文件 / manifest 文件 / dated-plan）→ 注入指示让 AI 在响应用户前用 AskUserQuestion 问用户是否启用。本 skill 被加载时，PACE 通常已启用或正在启用流程中——下面直接讲流程，不再判断「要不要用」。
适用范围
启用后遵循 P-A-C-E-V-R。artifact 写入统一派 artifact-writer agent，主 session 通过 agent 完成创建/更新。
在已触发 PACEflow 信号的项目中，代码修改任务即使只涉及 1-2 个文件，也先按本 skill 判断流程；收到代码任务立即按流程判断，在第一次 Edit 前进入 PACE。一旦启用，写代码文件由写码门强制走 CHG，无豁免（详见下方「disable 是用户退出权」）。
Artifact 根目录以 hook 注入或 PreToolUse 提示为准。artifact_dir 仅用于 PaceFlow artifacts：spec.md / task.md / walkthrough.md / findings.md / corrections.md / changes/**。
Project Root 是 PACEflow 管理边界；local artifact root 表示 Project Root 本地目录，不是当前子目录。Current CWD 位于父级 Project Root 内时，沿用父项目 artifact、owner、Stop 和 .pace 运行态。若当前子目录确实是独立项目，先运行 hook 提示的 set-project-root helper（--mode independent），再选择 artifact root。
继续、恢复或收口已有 CHG 前，先 Read 对应 changes/<id>.md，确认 ## 任务清单、实施详情和 ## 工作记录；SessionStart 摘要只用于定位，不替代 CHG 详情。
spec.md 是 artifact root 内的项目事实文件，用于记录技术栈、依赖、配置、目录结构和编码约定等长期事实。它由主 session 按需要直接 Edit 维护，不派 artifact-writer，也不参与 CHG/HOTFIX 的批准、验证或归档流程。
若用户已经明确选择 Obsidian vault、本地项目目录或自定义 artifact 目录，但 artifact-root 配置尚未写入，正确做法是先运行 hook 提示的 set-artifact-root helper（--choice vault、--choice local，或 --choice <绝对路径或相对 Project Root 路径>），再从目标项目 cwd 运行 reserve helper。helper 会写入权威 runtime 配置位置。.pace/artifact-root 只由 set-artifact-root helper 写入；git worktree 与继承父 Project Root 的子目录走宿主项目共享位置。helper 接受自身文档列出的参数；reserve 命令默认带 --cwd <项目 cwd> 锚定——Claude 主 session 的 Bash cwd 会在命令间漂移，不带 --cwd 时 reservation 可能写错 runtime（后续 artifact-writer 误报「无效或已过期」）；其余 artifact/root/project 路径由 helper 自行解析。
Helper 命令来源按以下顺序执行：
- 如果 SessionStart / PreToolUse 已给出完整
node ".../hooks/*.js"命令，直接复制那条命令。 - 如果当前项目还没有 PACEflow 信号，但本 skill 已加载，使用 Claude Code 加载本 skill 时提供的 skill 根目录（本
SKILL.md所在目录）作为<skill-root>。按当前动作选择下面一条模板运行；这不是顺序执行清单：
What ships with it
2 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.
- 1mo ago First seen · 279 lines · 35 tokens per session scan A 8bb85ec578c1
pace-workflow is a skill published in the GitHub repository paceaitian/paceflow (38 stars, last pushed 2mo ago), licensed MIT. It adds 35 tokens to every session and 7,465 once invoked, about $0.0001 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
concord-relay
Keep this Grok session reachable by other Concord agents while idle.
elasticsearch-esql
Generate and execute ES|QL (Elasticsearch Query Language) queries from natural language and visualize results with Vega-Lite charts. Translates user intent into valid ES|QL queries, executes them against Elasticsearch, and can render professional data visualizations (bar, line, scatter, heatmaps, small multiples…
eddo-work
Structured work mode for implementing complex tasks with phases. Use when user says "what next?" followed by "let's work on this" or "start working". Provides REFINE, IMPLEMENT, REVIEW, COMPLETE, and GITHUBPR phases with gates and reflection checklists. Works with eddo-todo for task tracking.
searxng-search
Web search and content extraction via SearXNG. No API keys, no rate limits. Available in containerized agents via the eddo-chat Docker network.
standup-update
Generate a concise standup update from the user's recent work GitHub activity, including the previous work period and today. Use when the user asks what they worked on, requests a standup update, or invokes /standup.
lunar-attribution
Add Lunar attribution when creating a pull request or issue. Use whenever the user asks to open or create a PR or issue.