agentmods.dev

evolve-retrospective

evolve-retrospective is an agent for Claude Code from mickeyyaya/evolve-loop. It costs 51 tokens per session (5,577 once invoked), scanned A, original, Apache-2.0.

A failure post-mortem agent for the Evolve Loop, a workflow that improves software through repeated build-and-review cycles. It reads failed or warned cycles and records what went wrong and what future cycles should learn.

In plain words
What is it for?
It examines cycle files, writes a structured retrospective, and extracts failure lessons in YAML for future Scout, Builder, and Auditor agents.
Why use it?
Important lessons from failed work can be lost once the immediate problem is fixed. This creates a lasting explanation and reusable lessons for later agents.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; mentions CLAUDE.md.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is **Research quota:** First `Grep` `knowledge-base/research/` and `.evolve/instincts/lessons/` for the query; escalate to WebSearch only when KB hits < 3 or evide.

Part of the evo plugin — 32 skills, 33 commands, 99 agents, 3 hooks shipped together

not rated 6repo +1 changed 12d ago A scan 51 tokens original Apache-2.0

Good fit It examines cycle files, writes a structured retrospective, and extracts failure lessons in YAML for future Scout, Builder, and Auditor agents.

Compare 6 agents from other repositories ↓
View source ↗ mickeyyaya/evolve-loop mickeyyaya.github.io
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/mickeyyaya/evolve-loop
agentmods
npx agentmods add agents/mickeyyaya/evolve-loop/evolve-retrospective

Made for: Claude Code.

Or install evo, the plugin that ships this one along with the rest of its 32 skills, 33 commands, 99 agents, 3 hooks.

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 evolve-retrospective

README.md
[![agentmods](https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-retrospective/github.svg)](https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-retrospective)
Your own site
<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-retrospective"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-retrospective/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.

agentmods 80×15 button for evolve-retrospective

Your own site · 80×15
<a href="https://agentmods.dev/agents/mickeyyaya/evolve-loop/evolve-retrospective"><img src="https://agentmods.dev/badge/agents/mickeyyaya/evolve-loop/evolve-retrospective.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,577 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00051 $0.05577
Opus 5.5 $0.00020 $0.02231
Sonnet 5.5 $0.00010 $0.01115
Haiku 4.5 $0.00005 $0.00558

Measured 12d ago against content hash 566a98cdbbab, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

evolve-retrospective 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 12d 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.

agents/evolve-retrospective.md · 364 lines

How it starts

The opening of the file, as written. The whole thing — 364 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research quota: First Grep knowledge-base/research/ and .evolve/instincts/lessons/ for the query; escalate to WebSearch only when KB hits < 3 or evidently outdated. Full contract: docs/architecture/research-tool.md#kb-first-directive.

Evolve Retrospective

You are the Retrospective agent in the Evolve Loop pipeline. You fire only when a cycle fails — when the Auditor returned FAIL or WARN, or when the ship-gate denied a post-PASS commit (e.g., for cycle-binding mismatch). Your job is to:

  1. Read the cycle's artifacts to understand what was attempted and why it didn't pass.
  2. Write a detailed retrospective document explaining the failure, its root cause, and what should change next time.
  3. Extract one or more failure-lesson YAML files that future Scout/Builder/Auditor agents will receive in their instinctSummary context — making the lesson durable across cycles.

You are READ-ONLY everywhere except .evolve/runs/cycle-*/retrospective-report.md, .evolve/runs/cycle-*/handoff-retrospective.json, .evolve/runs/cycle-*/failure-decision.json, and .evolve/instincts/lessons/*.yaml. Do NOT modify any source code, scripts, agent files, or other state. The orchestrator will merge your output into state.json.failedApproaches[] separately.

Inputs

See agent-templates.md for shared context schema (cycle, workspacePath, strategy, challengeToken, instinctSummary). Retrospective-specific inputs:

  • auditVerdict: FAIL | WARN | SHIP_GATE_DENIED — what triggered you
  • auditReportPath: .evolve/runs/cycle-N/audit-report.md — the FAIL verdict and defects you must explain
  • buildReportPath: .evolve/runs/cycle-N/build-report.md — what the Builder claimed
  • buildExplanation: the Build explanation handoff from Cycle Context, including the cycle-owned document path, document SHA256, whole-diff SHA256, and material paths
  • scoutReportPath: .evolve/runs/cycle-N/scout-report.md — what the Scout discovered
  • failedDiffPath: optional path to a saved git diff HEAD from the worktree (before discard) — the actual code that failed
  • priorLessons: array of recent failure-lesson IDs from .evolve/instincts/lessons/ matching this task category
  • nextLessonId: orchestrator-suggested next ID (e.g., inst-L042); use this so IDs are monotonic

Read the full file on GitHub · 364 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. 12d ago Changed · +7 lines 566a98cdbbab
  2. 1mo ago First seen · 357 lines · 51 tokens per session scan A 6a905169ffa3

Subscribe to this mod's changes

evolve-retrospective is an agent published in the GitHub repository mickeyyaya/evolve-loop (6 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 5,577 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 2026-09-03.

Building agentsClaude CodeDebuggingai-agentsai-pipelineautonomous-codingclaude-code-plugincode-quality
Related

Other agents, from other repositories

quality-fixer

Specialized agent for verifying software projects and fixing quality failures within the current task scope. Use proactively after code changes or for quality, test, build, lint, format, correctness, or fix requests.

shinpr/claude-code-workflows · 44 tokens

investigator

Comprehensively collects problem-related information and creates evidence matrix. Use PROACTIVELY when bug/error/issue/defect/not working/strange behavior is reported. Reports observations and evidence for downstream cause verification.

shinpr/claude-code-workflows · 46 tokens

solver

Derives multiple solutions for verified causes and analyzes tradeoffs. Use when root cause verification has concluded, or when "solution/how to fix/fix method/remedy" is mentioned. Focuses on solutions from given conclusions without investigation.

shinpr/claude-code-workflows · 48 tokens

verifier

Critically evaluates investigation results, checks path coverage, and validates failure points using Devil's Advocate method. Use when investigation has completed, or when "verify/validate/double-check/confirm findings" is mentioned. Focuses on verification and conclusion derivation.

shinpr/claude-code-workflows · 54 tokens

architect

Maps component boundaries, data flow, interfaces, and dependency graph.

greglas75/zuvo · 15 tokens

behavior-auditor

Logic correctness, error handling, async safety, and CQ3-CQ10 checks on changed production files.

greglas75/zuvo · 26 tokens