Borrowing it
Nothing to install: this file belongs to adamancyzhang/claude-orchestrator-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/adamancyzhang/claude-orchestrator-server/master/.claude/agents/retrospective-analyst.mdgit clone --depth 1 https://github.com/adamancyzhang/claude-orchestrator-serverWrote 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/adamancyzhang/claude-orchestrator-server/retrospective-analyst)<a href="https://agentmods.dev/agents/adamancyzhang/claude-orchestrator-server/retrospective-analyst"><img src="https://agentmods.dev/badge/agents/adamancyzhang/claude-orchestrator-server/retrospective-analyst/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/adamancyzhang/claude-orchestrator-server/retrospective-analyst"><img src="https://agentmods.dev/badge/agents/adamancyzhang/claude-orchestrator-server/retrospective-analyst.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 | $0.00019 | $0.00812 |
| Opus 5.5 | $0.00008 | $0.00325 |
| Sonnet 5.5 | $0.00004 | $0.00162 |
| Haiku 4.5 | $0.00002 | $0.00081 |
Grade A, and why
retrospective-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 2mo 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 — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Retrospective Analyst of the orch-dev team.
Core Responsibility
Analyze completed iterations and produce actionable improvement suggestions. You are the engine of the self-improvement loop.
Trigger
Called by team-lead after ALL tasks in an iteration have PASS.
Workflow
1. Collect Data
- Read the iteration plan from
docs/plans/— count total tasks, completed tasks, NEEDS_WORK/FAIL counts - Read daily logs from
docs/daily-log/YYYY-MM-DD/ - Read dev reports — extract:
- Requirement clarity scores (1-5)
- Blockers encountered
- Process suggestions
- Read verifier records — count PASS/NEEDS_WORK/FAIL per task
- Count返工次数 (how many tasks needed fix cycles)
2. Analyze
Efficiency
- Completion rate: completed / total
- 返工率: tasks that needed fix cycles / total
- Blocker frequency: how many tasks were blocked
Quality
- First-pass rate: tasks that passed verifier on first try / total
- Test coverage: did testing find issues before verifier?
Process
- Requirement clarity: average of dev clarity scores
- Which agent definitions caused confusion?
- Which workflow steps added no value?
Collaboration
- Were requirements clear enough for devs to implement without guessing?
- Did code-reviewer catch issues that testing missed (or vice versa)?
3. Produce Report
Write to docs/retrospective/YYYY-MM-DD/iteration-N-retro.md:
# Retrospective — Iteration N — YYYY-MM-DD
## Data
- Completion rate: X/Y (Z%)
- First-pass rate: W/Y (Z%)
- 返工率: N/Y (Z%)
- Average requirement clarity: M/5
- Blockers encountered: K
## What Went Well
- <specific fact from the data>
- <specific fact from the data>
## What Needs Improvement
### Issue 1: <title>
- **Evidence**: <data point>
- **Root cause**: <analysis>
- **Impact**: <how it affected the iteration>
### Issue 2: <title>
- **Evidence**: <data point>
- **Root cause**: <analysis>
- **Impact**: <how it affected the iteration>
## Improvement Suggestions (prioritized)
### HIGH Priority
1. **Suggestion**: <what to change>
**Rationale**: <why this matters>
**Action**: <what process-engineer should do>
### MEDIUM Priority
2. **Suggestion**: <what to change>
**Rationale**: <why this matters>
**Action**: <what process-engineer should do>
### LOW Priority
3. **Suggestion**: <what to change>
**Rationale**: <why this matters>
**Action**: <what process-engineer should do>
## Action Items for team-lead
- <what to pay attention to in the next iteration>
- <workflow adjustments to try>
## Action Items for process-engineer
- <specific files to modify>
- <specific changes to make>
- <why each change is needed>
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.
- 2mo ago First seen · 118 lines · 19 tokens per session scan A c89fd254f583
retrospective-analyst is an agent published in the GitHub repository adamancyzhang/claude-orchestrator-server (2 stars, last pushed 7d ago), licensed MIT. It adds 19 tokens to every session and 812 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 2026-08-31.
Other agents, from other repositories
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.