What is harness-retro?

A post-task reviewer that studies how an engineering task was carried out and looks for repeated errors or process problems. It separates issues in the project from issues in the task-running system.

Use it after complex tasks to review commits, reversals, timing, and execution notes. It helps draft ready-to-use project rules or issue reports for recurring problems.

It turns repeated execution mistakes into concrete rules instead of treating each failure as an isolated event. It also preserves useful practices that worked well.

harness-retro — Agent for Claude Code by stone16

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/stone16/harness-engineering-skills

Made for: Claude Code.

Or install harness-engineering-skills, 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/stone16/harness-engineering-skills/harness-retro/github.svg)](https://agentmods.dev/agents/stone16/harness-engineering-skills/harness-retro)

Your own site

<a href="https://agentmods.dev/agents/stone16/harness-engineering-skills/harness-retro"><img src="https://agentmods.dev/badge/agents/stone16/harness-engineering-skills/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/stone16/harness-engineering-skills/harness-retro"><img src="https://agentmods.dev/badge/agents/stone16/harness-engineering-skills/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 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.

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

Copies of this mod

1 near-identical copy found in the catalogue:

harness-retro — 100% identical, 0 lines differ

plugins/harness-engineering-skills/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 stone16/harness-engineering-skills (32 stars, last pushed 2d 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Analytics and metrics Building agents Claude Code Code review ai-code-review claude claude-code-plugin code-quality

code-reviewer

Reviews completed implementation for governing-source compliance, scope economy, repository quality policy, and material code correctness. Use after implementation or when review/implementation check/compliance is requested.

shinpr/claude-code-workflows · 38 tokens

code-verifier

Verifies repository-backed claims and implementation feasibility in PRDs, Design Docs, or Work Plans. Use before document review, after implementation, or for reverse-engineered artifact verification.

shinpr/claude-code-workflows · 39 tokens

release-manager

Cuts a brooks-lint release: sets the version in package.json, propagates it across the four plugin manifests and every version-bearing text file via npm run bump, writes the CHANGELOG entry, re-validates, then commits, pushes to main, tags, and publishes the GitHub release. Final pipeline stage of the brooks-harness…

hyhmrright/brooks-lint · 85 tokens

harness-retro