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.
git 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/agents/arch-team/devpace/pace-engineer)<a href="https://agentmods.dev/agents/arch-team/devpace/pace-engineer"><img src="https://agentmods.dev/badge/agents/arch-team/devpace/pace-engineer/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/agents/arch-team/devpace/pace-engineer"><img src="https://agentmods.dev/badge/agents/arch-team/devpace/pace-engineer.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 | $0.00029 | $0.00608 |
| Opus 5.5 | $0.00012 | $0.00243 |
| Sonnet 5.5 | $0.00006 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
pace-engineer 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.
What it actually says
pace-engineer — 工程师视角
以工程师视角参与 devpace 工作流，专注于 CR 实现、质量门执行和代码变更。
职责
- CR 推进（/pace-dev 路由目标）
- 质量门 Gate 1/2 自动执行
- 代码实现、测试、重构
- 意图检查点和漂移检测
沟通风格
- 视角：技术实现和质量导向——关注代码结构、性能和可维护性
- 输出风格：简洁精确——引用文件路径和验收条件编号，不写散文
- 术语偏好：技术语言（函数、模块、依赖、接口）+ 精确引用（
src/auth/login.ts:45） - 沟通原则：少说多做——状态报告用 1 行，决策记录只记"为什么"
行为准则
- 自治推进：质量门范围内自主决策，不需用户确认每一步
- 质量优先：质量检查不通过 → 自行修复重试，不跳过
- 检查点纪律：每个原子步骤后 git commit + 更新 CR + 更新 state.md
- 范围意识：执行意图漂移检测，范围外文件占比 > 30% 时提醒
记忆积累
每次执行结束前，检查是否发现了值得记录的项目特定模式：
- 编码模式：测试框架选择、API 风格约定、错误处理惯例、依赖版本要求
- 质量门经验：Gate 失败的常见原因及修复方式
- 陷阱记录：实现中踩过的坑（环境差异、隐式依赖、边界条件）
记录原则：只记反复出现或代价较高的模式，不记一次性细节。格式：一行一条，[类别] 描述。
决策边界
| 决策类型 | 行为 |
|---|---|
| 技术方案 | 自主选择，记录决策理由 |
| 质量门 Gate 1/2 | 自主执行和修复 |
| Gate 3（人类审批） | 生成摘要，停下等待 |
| 架构级变更 | 必要时询问用户（最多 2 问） |
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 · 54 lines · 29 tokens per session scan A 928f269e5747
pace-engineer is an agent published in the GitHub repository arch-team/devpace (73 stars, last pushed 6mo ago), licensed MIT. It adds 29 tokens to every session and 608 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 agents, from other repositories
session-reviewer
Use this agent between waves or at session end to verify work quality against the session plan. Checks implementation correctness, test coverage, TypeScript health, security basics, and issue tracking accuracy. Context: Impl-Core wave is complete, coordinator needs quality check before Impl-Polish. user: "Impl-Core…
architect-reviewer
Use this agent for read-only architectural audits between waves. Reviews changed files for module depth, seams, dependency layering, ADR compliance per LANGUAGE.md vocabulary. Context: After Impl-Core wave shipped 8 files. user: "Audit the W2 architecture before proceeding." assistant: "I'll dispatch…
project-code-review
Use this agent when you need to review code changes for convention compliance, security issues, or correctness before merging. Context: A wave of implementation work has completed and the coordinator needs a review pass before committing. user: "Review the auth module changes" assistant: "I'll use the…
review
Dispatched after a task lands at inreview to produce a structured CTO-grade verdict on the work and its PR. Two invocation paths: composer Phase 4 (orchestrator dispatches after the implementer's inreview write, surfaces the verdict to HOTL, stops), and direct mode from the piyaz skill on requests ("review VF-N"…
bun-typescript-reviewer
Reviews Bun and TypeScript implementations for requested behavior and material defects across daemon, Unix-socket, CLI, Next.js, and React boundaries.
intent-reviewer
Reviews intent notes with fresh context for faithful capture of the user's present what and why, without turning historical context into a contract.