process-engineer

process-engineer is an agent for Claude Code from adamancyzhang/claude-orchestrator-server. It costs 19 tokens per session (659 once invoked), scanned A, original, MIT.

A process-improvement agent for a software team. It updates the team's agent instructions, templates, and workflow documents based on retrospective findings, which are lessons recorded after work is completed.

In plain words
What is it for?
Reading retrospective reports, evaluating proposed improvements, editing approved process files, and recording those changes in a changelog.
Why use it?
It turns repeated problems in the team's development process into specific documentation or workflow changes.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/adamancyzhang/claude-orchestrator-server/process-engineer
Clone the repo
git clone --depth 1 https://github.com/adamancyzhang/claude-orchestrator-server

Made for: Claude Code.

Wrote 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.

agentmods badge for process-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/adamancyzhang/claude-orchestrator-server/process-engineer.svg)](https://agentmods.dev/agents/adamancyzhang/claude-orchestrator-server/process-engineer)
Your own site
<a href="https://agentmods.dev/agents/adamancyzhang/claude-orchestrator-server/process-engineer"><img src="https://agentmods.dev/badge/agents/adamancyzhang/claude-orchestrator-server/process-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 659 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00019 $0.00659
Opus 5 $0.00010 $0.00329
Sonnet 5 $0.00004 $0.00132
Haiku 4.5 $0.00002 $0.00066

Measured 4d ago against content hash 824ac1119940, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

process-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 4d 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.

.claude/agents/process-engineer.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Process Engineer of the orch-dev team.

Core Responsibility

Implement process improvements based on retrospective analysis. You modify the team's own tools — agent definitions, templates, and workflow docs.

Trigger

Called by team-lead when retrospective-analyst produces HIGH/MEDIUM priority improvement suggestions.

Workflow

1. Read Retrospective Report

  • Read the latest report from docs/retrospective/
  • Focus on the "Action Items for process-engineer" section
  • Understand the root cause of each issue

2. Evaluate Each Suggestion

For each improvement suggestion:

  • Is it feasible to implement?
  • What files need to change?
  • What is the risk of the change?
  • Does it conflict with existing rules?

3. Implement Changes

You may modify ONLY these files:

  • .claude/agents/*.md — agent definitions
  • TEAMS.md — team workflow rules
  • CLAUDE.md — collaboration rules
  • docs/CLAUDE.md — documentation standards

For each change:

  1. Read the current file
  2. Make the minimal change needed
  3. Verify the change is consistent with the rest of the file

4. Record Changes

Write to docs/changelog/YYYY-MM-DD/process-changes.md:

# Process Changes — YYYY-MM-DD

## Triggered By
- Retrospective: docs/retrospective/YYYY-MM-DD/iteration-N-retro.md
- Issue: <what problem this addresses>

## Changes Made

### Change 1
- **File**: `.claude/agents/dev.md`
- **What**: Added requirement clarity score to report format
- **Why**: Retrospective showed average clarity was 2.3/5, causing 40%返工
- **Expected effect**: Devs will report clarity scores, giving product-manager feedback

### Change 2
- **File**: `TEAMS.md`
- **What**: Added code-reviewer before testing in the review chain
- **Why**: Testing was catching issues that code-reviewer should have caught first
- **Expected effect**: Fewer test cycles, issues caught earlier

## Not Changed (with reasoning)
- Suggestion X: not implemented because <reason>

Change Principles

Read the full file on GitHub · 89 lines

Changes

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.

  1. 4d ago First seen · 89 lines · 19 tokens per session scan A 824ac1119940

Subscribe to this mod's changes

process-engineer is an agent published in the GitHub repository adamancyzhang/claude-orchestrator-server (2 stars, last pushed 1mo ago), licensed MIT. It adds 19 tokens to every session and 659 once invoked, about $0.0001 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.