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 oeftimie/vv-claude-harness --skill harness-improvegit clone --depth 1 https://github.com/oeftimie/vv-claude-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/oeftimie/vv-claude-harness/harness-improve)<a href="https://agentmods.dev/skills/oeftimie/vv-claude-harness/harness-improve"><img src="https://agentmods.dev/badge/skills/oeftimie/vv-claude-harness/harness-improve/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.
<a href="https://agentmods.dev/skills/oeftimie/vv-claude-harness/harness-improve"><img src="https://agentmods.dev/badge/skills/oeftimie/vv-claude-harness/harness-improve.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00105 | $0.01530 |
| Opus 5 | $0.00053 | $0.00765 |
| Sonnet 5 | $0.00021 | $0.00306 |
| Haiku 4.5 | $0.00011 | $0.00153 |
Grade A, and why
harness-improve 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 11d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Improve
Adapted from harness-engineering's playbooks/improve-harness.md (CC BY 4.0):
improvement driven by an OBSERVED TRAJECTORY, never by a feature idea alone.
Non-harness projects: if .harness/ doesn't exist, stop and point the user at
/harness-init -- this whole loop depends on evidence only .harness/ provides
(Step 2); there is nothing to observe without it.
Guardrails (read before Step 1)
- Bounded claim: one before-and-after run supports only a bounded claim about THAT job, on THAT worker config, THAT day -- never generalize past what was actually observed.
- Retrieved-or-invoked check: a successful rerun says nothing about an instruction the trajectory never actually used. Before crediting an intervention, confirm it was genuinely retrieved (the file was read) or invoked (the hook fired, the check ran) during the rerun -- not just present on disk.
- No uncorroborated self-report: a model's own claim that it "understood" or "will do better" is not evidence. Only observed behavior counts.
Step 1: Record the Job Contract
Before touching anything, write down: the target job + revision (feature ID or
task description); the fixed worker config (.harness/harness.json's worker
block, F016/OVI-57, if present -- note "unrecorded" if absent, don't guess); a
representative job (the actual session/task under review); the accepted outcome
(what "done" looked like); the evidence available; the budget/stop conditions for
this improvement pass itself; the suspected gap (a hypothesis, not a conclusion
yet).
Step 2: Observe the Baseline
Gather evidence vv already has -- don't reconstruct from memory:
.harness/features.json:correction_cycles,scope_expansions,approaches_tried,failure_reasonon the job's feature(s)..harness/SESSION_INCOMPLETEhistory, if still present: what gaps got flagged and left open..harness/mld/*.mdentries (F014/OVI-54; P3.1's corroboration marker, when present):## Mistakes/## Learnings/## Desiresfrom past sessions on this job.- The actual session transcript, if still available.
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.
- 11d ago First seen · 125 lines · 105 tokens per session scan A fd4920d3f9dd
harness-improve is a skill published in the GitHub repository oeftimie/vv-claude-harness (19 stars, last pushed 19d ago), licensed MIT. It adds 105 tokens to every session and 1,530 once invoked, about $0.0005 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.