harness-improve

harness-improve is a skill for Claude Code from oeftimie/vv-claude-harness. It costs 105 tokens per session (1,530 once invoked), scanned A, original, MIT.

A measured improvement loop for projects managed by Harness, a system that records jobs and their execution history.

In plain words
What is it for?
Recording a job contract, checking the baseline, locating and classifying a gap, applying one intervention, verifying it, and deciding whether to keep or revise it.
Why use it?
It uses observed failures and reruns to identify the earliest broken handoff and test one targeted improvement.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths.

Part of the vv-harness plugin — 6 skills, 7 agents, 5 hooks shipped together

Good fit Recording a job contract, checking the baseline, locating and classifying a gap, applying one intervention, verifying it, and deciding whether to keep or revise it.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oeftimie/vv-claude-harness/harness-improve
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.

Any agent
npx skills add oeftimie/vv-claude-harness --skill harness-improve
Clone the repo
git clone --depth 1 https://github.com/oeftimie/vv-claude-harness

Made for: Claude Code.

Or install vv-harness, the plugin that ships this one along with the rest of its 6 skills, 7 agents, 5 hooks.

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.

agentmods badge for harness-improve

README.md
[![agentmods](https://agentmods.dev/badge/skills/oeftimie/vv-claude-harness/harness-improve/github.svg)](https://agentmods.dev/skills/oeftimie/vv-claude-harness/harness-improve)
Your own site
<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.

agentmods 80×15 button for harness-improve

Your own site · 80×15
<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>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,530 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce 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

Measured 11d ago against content hash fd4920d3f9dd, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

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.

skills/harness-improve/SKILL.md · 125 lines

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_reason on the job's feature(s).
  • .harness/SESSION_INCOMPLETE history, if still present: what gaps got flagged and left open.
  • .harness/mld/*.md entries (F014/OVI-54; P3.1's corroboration marker, when present): ## Mistakes / ## Learnings / ## Desires from past sessions on this job.
  • The actual session transcript, if still available.

Read the full file on GitHub · 125 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.

  1. 11d ago First seen · 125 lines · 105 tokens per session scan A fd4920d3f9dd

Subscribe to this mod's changes

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.

Related

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…

ChromeDevTools/chrome-devtools-mcp · 99 tokens

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.

open-metadata/OpenMetadata · 37 tokens

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.

emdash-cms/emdash · 43 tokens

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.

emdash-cms/emdash · 48 tokens

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…

zebbern/claude-code-guide · 71 tokens

byted-util-volcengine-detect-retry

An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.

bytedance/agentkit-samples · 101 tokens