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 arch-team/devpace --skill pace-syncgit clone --depth 1 https://github.com/arch-team/devpaceWrote 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/arch-team/devpace/pace-sync)<a href="https://agentmods.dev/skills/arch-team/devpace/pace-sync"><img src="https://agentmods.dev/badge/skills/arch-team/devpace/pace-sync/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/arch-team/devpace/pace-sync"><img src="https://agentmods.dev/badge/skills/arch-team/devpace/pace-sync.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00062 | $0.01143 |
| Opus 5.5 | $0.00025 | $0.00457 |
| Sonnet 5.5 | $0.00012 | $0.00229 |
| Haiku 4.5 | $0.00006 | $0.00114 |
Grade A, and why
pace-sync 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pace-sync — 外部工具同步
将 devpace 全部实体（Epic/BR/PF/CR）与外部项目管理工具同步。支持 GitHub（当前），设计为 Linear/Jira 可扩展。
与现有机制的关系
- /pace-dev 管理 CR 内部状态转换 → /pace-sync 将状态变化推送到外部
- /pace-change 管理变更操作 → /pace-sync 同步变更后状态到外部
- /pace-release 管理发布流程 → /pace-sync 同步发布状态到外部
- /pace-review Gate 2 结果 → /pace-sync Gate 结果自动推送（Comment + 标签）
- /pace-status 展示内部状态 → /pace-sync status 展示同步状态和外部链接
推荐使用流程
首次配置：setup → 日常同步：/pace-sync（智能同步）→ 查看状态：status
输入
$ARGUMENTS 解析为子命令 + 参数。
子命令
| 子命令 | 参数 | 说明 |
|---|---|---|
| sync | [--dry-run] | 智能同步（默认行为）：自动检测变更，呈现摘要，确认后执行。无参数时等价。 |
| link | 实体ID [#外部ID] | 关联实体与已有外部 Issue（支持 EPIC-xxx/BR-xxx/PF-xxx/CR-xxx；省略外部 ID 则智能匹配） |
| unlink | 实体ID | 解除实体与外部的关联 |
| status | [--all] | 查看同步状态（--all 显示全部实体类型，默认仅 CR） |
| setup | [--auto] | 引导式同步配置（--auto 跳过交互确认） |
| pull | 实体ID | 查询外部状态，提示用户是否更新 devpace（轻量检查） |
无参数时默认执行智能同步（sync）。
实体 ID 格式：EPIC-001、BR-002、PF-003、CR-004（前缀确定类型）。纯数字默认为 CR（向后兼容）。
流程
- 读取
.devpace/integrations/sync-mapping.md（不存在 → 引导setup） - 加载
skills/pace-sync/sync-procedures-common.md（始终加载） - 根据子命令，仅加载对应的 procedures 文件（均位于
skills/pace-sync/目录）：
| 参数 | 加载文件 |
|---|---|
sync / （空） |
skills/pace-sync/sync-procedures-entity.md（智能同步主流程） |
sync --dry-run |
skills/pace-sync/sync-procedures-entity.md（dry-run 模式） |
link |
skills/pace-sync/sync-procedures-link.md + skills/pace-sync/sync-procedures-entity.md（§1 ID 解析） |
unlink |
skills/pace-sync/sync-procedures-status.md + skills/pace-sync/sync-procedures-entity.md（§1 ID 解析） |
status [--all] |
skills/pace-sync/sync-procedures-status.md [+ skills/pace-sync/sync-procedures-entity.md] |
setup |
skills/pace-sync/sync-procedures-setup.md |
pull |
skills/pace-sync/sync-procedures-pull.md + skills/pace-sync/sync-procedures-entity.md（§1 ID 解析） |
Gate 结果同步（被动触发）：skills/pace-sync/sync-procedures-push-advanced.md
Auto-link/create（Hook 触发）：skills/pace-sync/sync-procedures-auto.md
输出
智能同步输出格式：
同步检测：
- 3 个实体有变更（CR-003 状态→developing, EPIC-001 完成度↑, PF-002 新增验收）
- 2 个新实体未关联（BR-003, CR-008）
- 7 个已关联且无变化
[用户确认后]
| 实体 | 类型 | 外部链接 | 操作 | 结果 |
|------|------|---------|------|------|
| EPIC-001 | Epic | [#10](URL) | 更新标签 | ✅ |
| BR-003 | BR | [#15](URL) | 新建 Issue | ✅ |
| CR-003 | CR | [#42](URL) | 更新标签 + Comment | ✅ |
汇总：3 已同步 / 2 新建 / 7 无变化
层级：2 个 sub-issue 关系已建立
What ships with it
17 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.
- _deprecated/sync-procedures-ci.md 2.8 KB
- scripts/compute-sync-diff.mjs 6.5 KB runs code
- scripts/ensure-labels.mjs 2.7 KB runs code
- scripts/extract-entity-metadata.mjs 18 KB runs code
- scripts/generate-issue-body.mjs 18 KB runs code
- scripts/manage-sub-issues.mjs 7.7 KB runs code
- scripts/shared-utils.mjs 7.0 KB runs code
- sync-adapter-github.md 9.8 KB
- sync-procedures-auto.md 3.5 KB
- sync-procedures-common.md 4.1 KB
- sync-procedures-entity.md 7.3 KB
- sync-procedures-link.md 5.5 KB
- sync-procedures-pull.md 1.7 KB
- sync-procedures-push-advanced.md 2.7 KB
- sync-procedures-push.md 2.8 KB
- sync-procedures-setup.md 2.4 KB
- sync-procedures-status.md 2.2 KB
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 · 84 lines · 62 tokens per session scan A 26dbe3175a66
pace-sync is a skill published in the GitHub repository arch-team/devpace (73 stars, last pushed 6mo ago), licensed MIT. It adds 62 tokens to every session and 1,143 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
gitlab-ops
Use this skill when performing VCS operations on GitLab or GitHub repositories — creating, updating, or closing issues and MRs, applying label taxonomy, running glab/gh CLI commands, or resolving project paths dynamically. Acts as the single source of truth for CLI command syntax and label conventions; consuming…
gitlab-portfolio
Use when you need a single-pane cross-repo health view across all vault-registered GitLab and GitHub projects. Discovers repos from overview.md frontmatter in /01-projects//, aggregates open issues, MRs, critical labels, and stale signals via parallel glab/gh calls, then writes an idempotent PORTFOLIO.md dashboard.…
session-end
Use this skill when performing a full session close-out: verifies all planned work against the agreed plan, creates issues for gaps, runs quality gates, commits cleanly, mirrors to GitHub, and produces a session summary. Triggered by /close command.
session-start
Use this skill when initializing a session for any project repo. Autonomously analyzes git state, VCS issues, SSOT files, branches, environment, and cross-repo status. Then presents structured findings with recommendations before development wave planning, or an operations contract for explicitly requested…
close
End session with verification, commits, and documentation.
recursive-spine-method
Use when a builder wants to learn or be reminded of the recursive-spine tracking convention — where work state lives (GitHub issues+milestones, never prose ledgers), the five principles, the module system, and how to design a repo's dialect. Pure knowledge; takes no actions.