harness-issue-prep

harness-issue-prep is a skill for Claude Code from oeftimie/vv-claude-harness. It costs 95 tokens per session (4,491 once invoked), scanned B, original, MIT.

An interactive workflow that checks and prepares a software specification before implementation. It can take information from a Linear issue, pasted text, or a local features.json file.

In plain words
What is it for?
Use it to verify, normalize, and mark a feature specification as ready for development, with optional Linear tracking and local output.
Why use it?
It helps uncover unclear or incomplete requirements before coding begins and records when a specification has passed review.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents.

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 Use it to verify, normalize, and mark a feature specification as ready for development, with optional Linear tracking and local output.

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-prep

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/oeftimie/vv-claude-harness/harness-issue-prep"><img src="https://agentmods.dev/badge/skills/oeftimie/vv-claude-harness/harness-issue-prep.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 95 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,491 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 $0.00095 $0.04491
Opus 5 $0.00048 $0.02246
Sonnet 5 $0.00019 $0.00898
Haiku 4.5 $0.00010 $0.00449

Measured 12d ago against content hash 914a3b8493f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade B, and why

harness-issue-prep 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 12d 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-prep/SKILL.md · 389 lines

How it starts

The opening of the file, as written. The whole thing — 389 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Issue Prep

Follow these steps in order. This skill is the mint: it turns a spec (Linear issue, pasted text, or a features.json feature) into a verified, normalized spec, plus proof of that verification for whichever consumer needs it (local spec field, or a signed readiness stamp on Linear).

Step 1: Load configuration

Read the optional prep key from .harness/harness.json:

python3 - <<'PYEOF'
import json

try:
    with open(".harness/harness.json") as f:
        config = json.load(f)
except (FileNotFoundError, json.JSONDecodeError):
    config = {}

print(json.dumps(config.get("prep", {})))
PYEOF

No prep key at all: announce local-only mode up front (features.json output only; no stamp, no label, no kickstart) and proceed. A partial block (some sub-keys missing) is not an error: announce specifically which capabilities are off. prep.linear absent disables labeling; prep.stamp absent disables stamping (Step 7 becomes a no-op); prep.kick_command absent disables Step 8.

Step 2: Acquire the spec

Three sources, selected by the argument passed to this skill:

  • ISSUE-KEY (matches ^[A-Z]+-[0-9]+$): remote mode. Discover the connected Linear MCP's tools at runtime (never hardcode tool names; D12 in the implementation plan). Required capabilities checklist, all four must resolve:

    • fetch an issue by key, returning title, description, and labels
    • update an issue's description
    • create a comment on an issue
    • add and remove a label on an issue

    If any capability is missing, degrade to paste mode (below) with an explicit notice naming which capability was missing. If all four resolve, fetch the issue and hold title and description exactly as returned: no trimming, no whitespace normalization, ever. The stamp's spec_hash depends on the exact bytes (see ${CLAUDE_PLUGIN_ROOT}/schemas/readiness-stamp.md).

  • F0NN: local mode. Load that feature from .harness/features.json; the spec under test is its description field. Its scope and depends_on travel along as context for the verification agent, not as part of the hashed spec.

  • No argument, or the Linear MCP is unavailable: paste mode. Ask the user to paste the spec text, and ask whether the destination is local (a new or updated feature) or a Linear issue they will paste the normalized result back into by hand.

Read the full file on GitHub · 389 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. 12d ago First seen · 389 lines · 0 tokens per session scan B 914a3b8493f1

Subscribe to this mod's changes

harness-issue-prep is a skill published in the GitHub repository oeftimie/vv-claude-harness (19 stars, last pushed 20d ago), licensed MIT. It adds 95 tokens to every session and 4,491 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

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens

projects

List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.

me2resh/apexyard · 24 tokens

magpie-security-issue-import-from-md

Open one or more tracking issues from a markdown file containing a batch of security findings. Each finding becomes one tracker landing in the Needs triage board column. The file itself is the full report — there is no inbound reporter to reply to and no PR to inspect.

apache/magpie · 73 tokens