README

README is an agent for Claude Code from couimet/rangeLink. It costs 0 tokens per session (1,360 once invoked), scanned A, original, MIT.

A set of custom coding assistants for the RangeLink project, including one that reviews whether tests check the right level of behavior.

In plain words
What is it for?
The listed assistant analyzes test files, identifies scope problems, checks utility-test coverage, proposes refactoring, applies approved changes using mocks, and reports test results.
Why use it?
It helps teams avoid tests that duplicate utility-function testing or depend too closely on implementation details, which can make tests brittle and less useful.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/couimet/rangelink/readme
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 README

README.md
[![agentmods](https://agentmods.dev/badge/agents/couimet/rangelink/readme.svg)](https://agentmods.dev/agents/couimet/rangelink/readme)
Your own site
<a href="https://agentmods.dev/agents/couimet/rangelink/readme"><img src="https://agentmods.dev/badge/agents/couimet/rangelink/readme.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,360 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01360
Opus 5 $0.00000 $0.00680
Sonnet 5 $0.00000 $0.00272
Haiku 4.5 $0.00000 $0.00136

Measured 5d ago against content hash cf58600c08da, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

README 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 5d 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/agents/README.md · 112 lines

How it starts

The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Custom Claude Code Agents

This directory contains custom subagents for the RangeLink project.

Available Agents

test-scope-fixer

Purpose: Detects and fixes badly scoped tests that test implementation details instead of mocking delegated utility functions.

When to use: When you have test files that directly test the behavior of utility functions instead of mocking them and testing only the delegation logic.

Usage:

Task(subagent_type="test-scope-fixer", prompt="Analyze <test-file-path>")

Workflow:

  1. Phase 1 (Analysis): Agent analyzes tests, identifies badly scoped ones, checks utility test coverage, and presents a detailed refactoring plan
  2. User reviews and approves the plan
  3. Phase 2 (Refactoring): Agent applies the changes (adds mocks, removes badly scoped tests, adds properly scoped tests)
  4. Phase 3 (Report): Agent runs tests and reports results

Key Features:

  • Detects tests that verify utility function implementation details
  • Checks for coverage gaps in utility test files
  • Uses jest.mock() for module-level mocking
  • Uses jest.spyOn() for per-test customization
  • Ensures each test asserts on mock calls (delegation verification)
  • Runs tests after refactoring to verify correctness

tc-implement

Purpose: Implements one QA TC ID end-to-end as an integration test. Traces the production code path, writes the test using __integration-tests__/helpers/, inserts in TC-ID ascending order in the right suite/ file, updates the YAML entry's automated: field, and runs the matching pnpm test:release:* command.

When to use: When you have a QA TC ID that needs an integration test. Works for any automated: value (false, assisted, or true — the last is useful for re-implementing a test file that was lost). Typical workflow: /tcs-definition (skill) drafts a batch of TCs in a scratchpad; tc-implement (agent) is invoked once per TC for short feedback loops.

Usage:

Task(subagent_type="tc-implement", prompt="bind-to-destination-013")

Read the full file on GitHub · 112 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. 5d ago First seen · 112 lines · 0 tokens per session scan A cf58600c08da

Subscribe to this mod's changes

README is an agent published in the GitHub repository couimet/rangeLink (10 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,360 tokens. 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.