rangeLink: Skill for Claude Code

.claude/skills/start-issue-hook/SKILL.md

start-issue-hook is a skill for Claude Code from couimet/rangeLink. It costs 26 tokens per session (504 once invoked), scanned A, original, MIT.

A planning hook for RangeLink's /start-issue command that checks existing QA test-case coverage. QA means checking that software behaves as expected, and a test case is a documented scenario to verify.

In plain words
What is it for?
Use it when planning extension features, fixes, or behavior changes to inspect existing test cases, map test IDs, and add a test-definition step or justification.
Why use it?
It helps issue plans account for missing or outdated tests before implementation begins. It also records why tests are unnecessary for changes that do not affect user-visible behavior.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is couimet/rangeLink's own configuration. It tells Claude Code how to work on rangeLink itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything rangeLink configures →

Reuse

Borrowing it

Nothing to install: this file belongs to couimet/rangeLink. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/couimet/rangeLink/main/.claude/skills/start-issue-hook/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/couimet/rangeLink

Made for: Claude Code.

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 start-issue-hook

README.md
[![agentmods](https://agentmods.dev/badge/skills/couimet/rangelink/start-issue-hook.svg)](https://agentmods.dev/skills/couimet/rangelink/start-issue-hook)
Your own site
<a href="https://agentmods.dev/skills/couimet/rangelink/start-issue-hook"><img src="https://agentmods.dev/badge/skills/couimet/rangelink/start-issue-hook.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 504 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 $0.00026 $0.00504
Opus 5 $0.00013 $0.00252
Sonnet 5 $0.00005 $0.00101
Haiku 4.5 $0.00003 $0.00050

Measured 8d ago against content hash 542627827ad0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

start-issue-hook 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 8d 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.

.claude/skills/start-issue-hook/SKILL.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Consulted automatically by /start-issue during context gathering. Adds QA TC coverage awareness to every issue plan.

Additional Context Gathering

Read packages/rangelink-vscode-extension/qa/qa-test-cases.yaml to understand current TC coverage. Note which feature sections exist and the highest -NNN per slug. Optionally glob packages/rangelink-vscode-extension/src/__integration-tests__/suite/*.test.ts to map existing test IDs by slug — this helps the plan reference which TCs already exist vs which need drafting.

Additional Plan Requirements

The plan must include EITHER:

  • A TC-definition step that invokes /tcs-definition to draft new or updated QA test cases — placed BEFORE implementation steps when feasible.
  • An explicit justification in "Assumptions Made" stating why TCs are not needed for this issue. Valid reasons: internal refactors that don't change user-visible behavior, tooling/infrastructure changes, CI/CD changes, documentation-only changes, dependency bumps with no behavioral impact, changes to .claude/ skills or agents that don't touch extension runtime code.

If the issue introduces, modifies, or fixes user-visible behavior (new features, changed commands, changed output, new settings, behavior-altering bug fixes), the TC-definition step is REQUIRED — do not skip with an assumption.

Where the Step Sits

Prefer placing /tcs-definition as the first plan step. The skill's draft phase is spec-elicitation — running it before implementation keeps the interview focused on what the feature should do rather than confirming what was built. The skill itself warns when the diff exceeds 1000 lines because the interview drifts from spec-elicitation to implementation-confirmation.

When the TC entries depend on implementation-defined details (schema, exact output format), move the /tcs-definition step after the implementation steps but still before /finish-issue.

The /tcs-definition step body should read:

Read the full file on GitHub · 38 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. 8d ago First seen · 38 lines · 26 tokens per session scan A 542627827ad0

Subscribe to this mod's changes

start-issue-hook is a skill published in the GitHub repository couimet/rangeLink (10 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 504 once invoked, about $0.0001 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.