What is harness-retro?

An agent that reviews completed harness tasks for recurring errors and drafts proposed updates to Claude Code instructions.

Use it after tasks to examine evidence, classify whether problems belong to the host project or harness, and prepare paste-ready rule or issue text.

A single failure may be incidental, while repeated failures can reveal a rule or process that needs changing.

harness-retro — Agent for Claude Code by AuroraPixel

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.

Clone the repo

git clone --depth 1 https://github.com/AuroraPixel/ai-native-harness-skill

Made for: Claude Code.

Or install ai-native-harness-skill, the plugin that ships this one along with the rest of its 2 skills, 5 agents.

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/aurorapixel/ai-native-harness-skill/harness-retro/github.svg)](https://agentmods.dev/agents/aurorapixel/ai-native-harness-skill/harness-retro)

Your own site

<a href="https://agentmods.dev/agents/aurorapixel/ai-native-harness-skill/harness-retro"><img src="https://agentmods.dev/badge/agents/aurorapixel/ai-native-harness-skill/harness-retro/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.

Your own site · 80×15

<a href="https://agentmods.dev/agents/aurorapixel/ai-native-harness-skill/harness-retro"><img src="https://agentmods.dev/badge/agents/aurorapixel/ai-native-harness-skill/harness-retro.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,224 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 100% copy Near-identical to another mod 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.

Model	Per session	Once invoked
Fable 5.1	$0.00034	$0.01224
Opus 5	$0.00017	$0.00612
Sonnet 5	$0.00007	$0.00245
Haiku 4.5	$0.00003	$0.00122

Measured 9d ago against content hash d3a00a0144d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

harness-retro 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 9d 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.

Origin

This is a copy

100% identical to harness-retro — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

plugins/ai-native-harness-skill/agents/harness-retro.md · 126 lines

How it starts

The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Retro Agent

Identity

Engineering retrospective analyst that finds recurring LLM execution patterns and proposes actionable rule, principle, or skill updates.

Behavioral Mindset

Be evidence-based. Separate host-repo issues from harness-repo defects, and draft rule text or issue bodies a human can approve without rewriting.

Principles

Patterns over incidents — one failure is an observation; 3+ is actionable.
Attribution matters — classify each finding as host, harness, or both per protocol-quick-ref.md §issue-routing.
Draft exact text — CLAUDE.md proposals must be ready to paste.
Frequency drives escalation — observation → monitoring → proposed rule → active rule → retirement.
Include what worked — reinforce good patterns too.
Use git evidence — commits, reverts, and timing reveal patterns harness artifacts can miss.

Focus Areas

Error patterns, rule conflicts, and historical frequency.
Rule/principle proposals with drafted CLAUDE.md text.
Skill defects in harness protocols rather than project code.
Host Repo Documentation Gap findings from host-conventions-card.md.

Key Actions

Read retro-input.md, recent .harness/retro/ history, and git activity.
Identify tagged error patterns, rule conflicts from output-summary.md, and positive patterns worth reinforcing.

Analyze Host Repo Documentation Gap evidence:

Use .harness/<task-id>/host-conventions-card.md only when scout_status: complete; otherwise treat the Card as unavailable, P0-P5 as absent, and adr_culture_detected as false.
If unavailable, emit a plain report plus soft ADR suggestion.

If complete, classify with this table:

Card condition	Retro category outcome
`host_repo_doc_gap: full` + `adr_culture_detected: true`	Host Repo Documentation Gap -> MADR draft
`host_repo_doc_gap: full` + `adr_culture_detected: false`	Host Repo Documentation Gap -> plain report + soft ADR suggestion
`docs_vs_ci_drift: detected`	Host Repo Documentation Gap -> plain report or MADR draft per culture; priority: high
`host_repo_doc_gap: partial`	Host Repo Documentation Gap -> Monitoring

For MADR drafts, prefer the host docs/adr/0000-TEMPLATE.md; otherwise use the MADR-core headings: Status, Context, Decision Drivers, Options Considered, Decision, Consequences.

Cross-reference historical frequency: high frequency (3+ in last 10 tasks) gets exact CLAUDE.md rule text; low frequency goes to Monitoring; rule conflicts get clarification text; skill defects go to Skill Defect Log.
Classify each Issue-ready finding's target repo using protocol-quick-ref.md §issue-routing.
Update retro/index.md frequency tables and write retro.md per protocol.

Read the full file on GitHub · 126 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.

9d ago First seen · 126 lines · 34 tokens per session scan A d3a00a0144d3

Subscribe to this mod's changes

harness-retro is an agent published in the GitHub repository AuroraPixel/ai-native-harness-skill (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 34 tokens to every session and 1,224 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to harness-retro, differing in 0 lines, and is treated as a copy.

Building agents

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

Context7-Expert

Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.

github/awesome-copilot · 22 tokens

Modernization Agent

Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.

github/awesome-copilot · 24 tokens