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/urmzd/dotfiles/run-eval-harnessnpx skills add urmzd/dotfiles --skill run-eval-harnessgit clone --depth 1 https://github.com/urmzd/dotfilesWrote 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/urmzd/dotfiles/run-eval-harness)<a href="https://agentmods.dev/skills/urmzd/dotfiles/run-eval-harness"><img src="https://agentmods.dev/badge/skills/urmzd/dotfiles/run-eval-harness.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 | $0.00134 | $0.00816 |
| Opus 5 | $0.00067 | $0.00408 |
| Sonnet 5 | $0.00027 | $0.00163 |
| Haiku 4.5 | $0.00013 | $0.00082 |
Grade A, and why
run-eval-harness 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 4d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Eval Harness
Own the whole run-monitor-parse-diff loop and return once with a complete summary. The user should never have to ask "check the current state".
1. Locate the harness
Search in order; stop at the first hit:
- Project docs: README, AGENTS.md, docs/ mentioning "eval".
- Task runners:
justfile,Makefile,package.jsonscripts,pyprojectscripts with eval targets. - Convention paths:
evals/,eval/,benchmarks/, files matching*eval*.py|ts|go.
If multiple harnesses exist, pick the one the user named; otherwise list
them and pick the default documented in the repo. Note the dataset in use
(golden set path) and where reports land (for example eval_report*,
results/, run_log.jsonl).
2. Launch in the background
- Run via the documented entry point with the repo's own defaults; do not invent flags.
- Use a background shell so the session stays free; capture stdout to a log file in the scratchpad.
- Record start time, git commit, model or provider config in effect.
3. Monitor without spamming
Poll the log at an interval matched to expected runtime (a 10 minute run gets checks every 2 to 3 minutes, not every 15 seconds). Detect and report early: crash, auth failure, rate limiting (429 or backoff messages), or a stall with no new output for 3 poll cycles. On transient provider errors, retry the run once before reporting failure.
4. Parse into the normalized summary
Extract whatever subset the report provides:
| Metric | Notes |
|---|---|
| Pass / total, pass rate | Per strictness level if the harness has them |
| Latency P50 and P95 | Report both; never substitute mean |
| Tokens in / out per case | And totals |
| Cost per run and per case | From real configured prices, never hardcoded guesses |
| Failures | Case id, expected vs actual, one-line cause each |
5. Diff against the previous run
Find the most recent prior report or run log. Report: metric deltas, newly failing cases, newly passing cases, and whether config changed between runs (model, dataset, prompt version, commit). If no prior run exists, say so and record this one as the baseline.
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.
- 4d ago First seen · 84 lines · 134 tokens per session scan A 39391d128a80
run-eval-harness is a skill published in the GitHub repository urmzd/dotfiles (3 stars, last pushed 22d ago), licensed Apache-2.0. It adds 134 tokens to every session and 816 once invoked, about $0.0007 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
review-code
Standalone code review for any scope — PR number, branch, file paths, or current changes. Synthesizes intent, runs 10 parallel specialized agents, and presents actionable findings with a verdict. For PR scope, optionally posts the review to GitHub with inline comments.
coding
Principles for writing and designing code, covering API and abstraction design, naming, comment discipline, and standards of evidence for claims about code behavior. Use whenever the task is to write or modify code, design an API or software architecture, or review code.
review-prs
Fetch and present a prioritized summary of all PRs awaiting the current user's review across the relevant projects and provide an interactive workflow helping the user phrase and post inline review comments and overall review decisions.
review-converge
Autonomously review and fix the current branch or specified scope in iterative rounds until clean, leaving all changes in the working tree. Escalates only genuine design decisions. Ends with a transparent report of every round, every fix, and anything it couldn't resolve — persisted to .outputs/.
review-pr-comments-converge
Fetch PR review comments, validate each against the actual code, auto-fix obvious issues, and escalate genuine design decisions. Leaves all changes in the working tree. Use when you want to action reviewer feedback autonomously.
write-ticket-description
Voice guide for writing issue/ticket/task/epic descriptions. Use this skill for ALL issue creation — GitHub issues, Jira tasks, Monday tasks, Linear tasks, and epics. Contains section structure, voice rules, and anti-patterns. Never write ticket descriptions without invoking this skill first.