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.
npx agentmods add skills/mifunedev/openharness/retronpx skills add mifunedev/openharness --skill retrogit clone --depth 1 https://github.com/mifunedev/openharnessWrote 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/skills/mifunedev/openharness/retro)<a href="https://agentmods.dev/skills/mifunedev/openharness/retro"><img src="https://agentmods.dev/badge/skills/mifunedev/openharness/retro.svg" alt="Measured on agentmods" 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 | $0.00154 | $0.03825 |
| Opus 5 | $0.00077 | $0.01912 |
| Sonnet 5 | $0.00031 | $0.00765 |
| Haiku 4.5 | $0.00015 | $0.00382 |
Grade A, and why
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 today.
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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retro
Scientific session-closing retrospective. Turn the current conversation's signals into falsifiable hypotheses, test each against session evidence (for and against), assign a verdict and confidence, and nominate only the supported, sufficiently-confident ones as candidate probes under .oh/evals/probes/.
/retro is report-only. It emits its report to the terminal and writes no file at all. There is no durable lessons ledger and no dated run log; code is the source of truth, and a lesson that matters graduates to a probe under .oh/evals/probes/. A lesson that cannot be argued into a probe is spoken once and left in the transcript.
Use the self-contained helper in ${CLAUDE_SKILL_DIR}/scripts/ for deterministic checks; use ${CLAUDE_SKILL_DIR}/references/report-schema.md as the output contract.
When to use
/retroinvoked explicitly to close a session.- Proactively, after a session that produced decisions, surprises, regressions, or failure modes the next agent would benefit from knowing.
When NOT to use
/audit harness— audits harness code health via four parallel sub-agents. That is a structural audit, not a behavioral/conversational pass./audit context— scores the default-loaded context budget across four dimensions. It trims files, not behaviors./audit skills— scores individual skills for staleness. It reviews skill quality, not session outcomes./wiki lint— health-checks the wiki corpus for staleness and broken links. It curates the wiki, not the session.- Trivial sessions — if the session contained only mechanical read-only queries or single-command invocations with no surprises, announce the skip and stop.
Key boundary: /retro is session-scoped reflection. The lint/audit skills above are the deep-dive tooling it points at — not what it runs. It is the only skill whose domain is current-session signals → falsifiable hypotheses → probe candidates.
Scope
Current conversation only. /retro does not read prior sessions or the ~/.claude/projects/... auto-memory store. It works from what is already in context.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed · +23 lines 8dae7958d23a
- 4d ago First seen · 252 lines · 154 tokens per session scan A d5965c388103
retro is a skill published in the GitHub repository mifunedev/openharness (36 stars, last pushed yesterday), licensed Apache-2.0. It adds 154 tokens to every session and 3,825 once invoked, about $0.0008 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.
Other skills, from other repositories
arxiv-search
Searches arXiv for preprints and academic papers, retrieves abstracts, and filters by topic. Use when the user asks to find research papers, search arXiv, look up preprints, find academic articles in physics, math, CS, biology, statistics, or related fields.
data-visualization
Use for creating publication-quality charts and multi-panel analysis summaries. Triggers when tasks involve visualizing data, plotting results, creating charts, or producing visual reports from analysis output.
cuml-machine-learning
Use for GPU-accelerated machine learning on tabular data using NVIDIA cuML. Triggers when tasks involve classification, regression, clustering, dimensionality reduction, or model training on datasets.
blog-post
Writes and structures long-form blog posts, creates tutorial outlines, and optimizes content for SEO with cover image generation. Use when the user asks to write a blog post, article, how-to guide, tutorial, technical writeup, thought leadership piece, or long-form content.
social-media
Drafts engaging social media posts, writes hooks, suggests hashtags, creates thread structures, and generates companion images. Use when the user asks to write a LinkedIn post, tweet, Twitter/X thread, social media caption, social post, or repurpose content for social platforms.
remember
Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…