harness-issue-debug

harness-issue-debug is a skill for Claude Code from oeftimie/vv-claude-harness. It costs 103 tokens per session (2,292 once invoked), scanned B, original, MIT.

A live repair skill for work that has failed or been parked, using either a harness feature ID or a Linear issue key. A harness is the project system that stores feature and failure context; Linear is an issue-tracking service.

In plain words
What is it for?
Debugging failed harness features, repairing parked Linear issues, checking out the relevant branch, and returning the work to the external runner.
Why use it?
It gathers the failure details and opens the relevant work so you can correct the implementation or the specification behind it.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

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

Good fit Debugging failed harness features, repairing parked Linear issues, checking out the relevant branch, and returning the work to the external runner.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add oeftimie/vv-claude-harness
Claude Code
/plugin install vv-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-issue-debug

README.md
[![agentmods](https://agentmods.dev/badge/skills/oeftimie/vv-claude-harness/harness-issue-debug/github.svg)](https://agentmods.dev/skills/oeftimie/vv-claude-harness/harness-issue-debug)
Your own site
<a href="https://agentmods.dev/skills/oeftimie/vv-claude-harness/harness-issue-debug"><img src="https://agentmods.dev/badge/skills/oeftimie/vv-claude-harness/harness-issue-debug/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-issue-debug

Your own site · 80×15
<a href="https://agentmods.dev/skills/oeftimie/vv-claude-harness/harness-issue-debug"><img src="https://agentmods.dev/badge/skills/oeftimie/vv-claude-harness/harness-issue-debug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 103 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,292 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00103 $0.02292
Opus 5 $0.00051 $0.01146
Sonnet 5 $0.00021 $0.00458
Haiku 4.5 $0.00010 $0.00229

Measured 10d ago against content hash be5916861133, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

harness-issue-debug scanned grade B with 1 finding 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 10d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

f"fix with: chmod 600 {key_file}",
skills/harness-issue-debug/SKILL.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Issue Debug

Opens a live, interactive repair session on a piece of work that stopped: a harness feature marked failed, or a Linear issue the external runner parked after exhausting its self-heal attempts. This skill is the hands-on counterpart to harness-issue-prep: where harness-issue-prep fixes a spec before implementation starts, harness-issue-debug fixes an implementation (or the spec behind it) after something already went wrong.

Mode is selected by the shape of the argument:

  • F0NN (matches a feature id in .harness/features.json): local mode.
  • An issue key matching ^[A-Z]+-[0-9]+$ (for example ENG-123): runner mode.

If the argument matches neither shape, ask which mode the user means before proceeding.

Local Mode (F0NN)

Step 1: Load context. Read the feature from .harness/features.json and surface, in one block, everything a debugging session needs before touching code:

Feature F0NN: [description]
Status: failed
Failure reason: [failure_reason]
Notes: [notes]
Correction cycles: [correction_cycles]
Scope: [scope]

Step 2: Check out the branch. If notes names a branch, check it out. If it does not, ask the user which branch to use before continuing; do not guess.

Step 3: Establish the baseline. Run ./.harness/init.sh to confirm the checked-out branch builds and to see the current failure state directly, not secondhand through failure_reason.

Step 4: Iterate the fix. This is a normal interactive session: write a failing test, implement, confirm green, refactor, repeat. No special ceremony beyond the harness's usual TDD discipline applies here; the only thing that distinguishes this session from any other feature work is that it starts from a known failure instead of a blank feature.

Step 5: Exit route. Exactly one of three, decided with the human present:

  • Fixed and the human is satisfied. Set status to "pending", not "passing"; the quality gate (verify-task-quality.sh on TaskCompleted) is what earns "passing", and this skill does not shortcut it. Clear failure_reason.
  • The spec was the real problem, not the code. Run harness-issue-prep F0NN to fix the description before any further implementation attempt.
  • Abandoned this session. Keep status: "failed". Update failure_reason with what was learned this round, even if the answer is still "unresolved": a stale failure_reason from a prior attempt is worse than an updated one that says what was ruled out.

Read the full file on GitHub · 182 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. 10d ago First seen · 182 lines · 103 tokens per session scan B be5916861133

Subscribe to this mod's changes

harness-issue-debug is a skill published in the GitHub repository oeftimie/vv-claude-harness (19 stars, last pushed 17d ago), licensed MIT. It adds 103 tokens to every session and 2,292 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it B with 1 finding (asks for root). 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