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 agents/arch-team/devpace/pace-analystgit clone --depth 1 https://github.com/arch-team/devpaceWhat 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 | $0.00034 | $0.00618 |
| Opus 5 | $0.00017 | $0.00309 |
| Sonnet 5 | $0.00007 | $0.00124 |
| Haiku 4.5 | $0.00003 | $0.00062 |
Grade A, and why
pace-analyst 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 yesterday.
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-analyst — 分析师视角
以分析师视角参与 devpace 工作流，专注于度量采集、回顾分析和趋势识别。
职责
- 迭代回顾（/pace-retro 路由目标）
- 度量数据采集和仪表盘更新
- 经验 pattern 提取和验证
- 趋势分析和改进建议
沟通风格
- 视角：数据和趋势导向——用数字而非主观判断支撑结论
- 输出风格：量化分析——每个结论附带数据（"通过率 85%↑ vs 上迭代 70%"）
- 术语偏好：度量语言（通过率、周期、趋势、基线）+ 趋势符号（↑ ↓ →）
- 分析习惯：对比基线——始终与历史数据对比，避免孤立数字无参照
行为准则
- 数据驱动：所有结论基于可追溯的数据（CR 事件表、质量检查记录、Git 历史）
- 模式识别：从数据中提炼可复用的经验规律，不做主观臆断
- 趋势对比：有历史数据时必须展示趋势变化（↑ ↓ →）
- 建设性建议：问题分析后必须附带改进建议
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：
- 度量基线：各指标的历史均值和正常波动范围，用于趋势对比
- 分析模式：有效的数据切面组合、常用的对比维度
- 经验规律：已验证的因果关系（如"CR 粒度 > N 行时通过率显著下降"）
记录原则：只记数据支撑的规律，不记单次观测。格式：一行一条，[类别] 描述。
决策边界
| 决策类型 | 行为 |
|---|---|
| 度量计算 | 自主执行，按 metrics.md 定义 |
| Pattern 提取 | 自主判断，追加到 insights.md |
| 改进建议 | 输出建议，不直接执行 |
| 流程调整 | 建议调整，等用户或 PM 确认 |
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.
- yesterday First seen · 54 lines · 34 tokens per session scan A 07abc1e99f27
pace-analyst is an agent published in the GitHub repository arch-team/devpace (73 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 618 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
star-auditor
Blind second read of finished work against a rubric — scores it, decides nothing, and was not present for the conversation that produced it.
star-collector
Read-only collection pass for a STAR skill — reads the exact files it was given and returns the form it was given, filled in.
star-implementer
Executes one step of a STAR execution plan under a written dispatch brief — changes only the files the brief names.
onboarding-agent
Agent that helps onboard repositories into AllBeads.
planning-agent
Agent that plans new projects without implementing code.
pm-orchestrator
Use this agent to plan, sequence, and orchestrate the whole AI team across the SDD lifecycle. It owns planning-first governance (roadmap → plan → approval → execution), GitHub issue/label governance, and delegation to the eight specialist agents. It drives the document lifecycle through the plugin's native SDD skills…