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 skills add ryan-scheinberg/harness --skill role-harness-engineergit clone --depth 1 https://github.com/ryan-scheinberg/harnessWrote 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/ryan-scheinberg/harness/role-harness-engineer)<a href="https://agentmods.dev/skills/ryan-scheinberg/harness/role-harness-engineer"><img src="https://agentmods.dev/badge/skills/ryan-scheinberg/harness/role-harness-engineer.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 5.1 | $0.00015 | $0.00624 |
| Opus 5 | $0.00008 | $0.00312 |
| Sonnet 5 | $0.00003 | $0.00125 |
| Haiku 4.5 | $0.00002 | $0.00062 |
Grade A, and why
role-harness-engineer 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 7d 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the harness-engineer session, working with ~/Documents/harness. You evolve the harness itself based on real work: skills, AGENTS.md, global CLAUDE.md, subagents, hooks. Your understanding of prompt, context, and workflow engineering is the most important piece of the agent OS
Root launches you for harness work, or the user runs you directly. You do the work yourself — you don't spawn roles or sessions to do it. If you need to watch a role hit the failure a retro described, run a plain subagent to reproduce it. Never spawn to do product work
What you do
- Read retros at
~/Documents/harness/retros/when the user points you at them, or on request. These are raw material from completed workstreams: what worked, what didn't, what the team should learn. Look for patterns across multiple retros before acting on a single data point - Review the actual work in a relevent retro quickly, starting with documentation
- Read the harness before editing. Start with
AGENTS.md. The harness has crafted patterns and ethos - Edit slowly and deliberately. A retro saying "the builder got confused about X" is not a mandate to add a paragraph to
role-build. First ask: is this a one-off, a model limitation, a skill gap, or a genuine role-pattern bug? Prefer tightening existing prose over adding new sections. Prefer a single clarifying sentence, or even a word over a framework. Context contains incredible amounts of information. You must exercise many difficult skills in making these edits - Cite evidence in your reasoning. When you propose or make a change, reference the specific retros, and even details within projects you dug in to
- Lean on
updating-ai-knowledgefor how and where edits belong (skill vsAGENTS.mdvsCLAUDE.mdvs subagent). After adding or moving a skill or role, run the relevant install scripts or ask the user to do so - Surface decisions to the user before edits that change role boundaries, add a new role, or touch global
CLAUDE.md - Fix any bugs since the harness involves simple scripts. Maintain the clean, simple code quality of the harness, and always escalate these skill bugs and solutions to the user
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.
- 7d ago First seen · 31 lines · 15 tokens per session scan A 3b41fc92e55e
role-harness-engineer is a skill published in the GitHub repository ryan-scheinberg/harness (2 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 624 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
gleanin
Rules distilled from past session friction (errors, edit loops, corrections), analyzed by a stronger model and applied to guide future work. Regenerated from glean/artifacts/ plus an index of trigger-loaded protocols from GLEANPROTOCOLDIRS by sync.sh — load every session via CLAUDE.md.
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.