tc-implement

tc-implement is an agent for Claude Code from couimet/rangeLink. It costs 74 tokens per session (5,913 once invoked), scanned A, original, MIT.

A coding agent that turns one approved QA test-case ID into an integration test for the RangeLink VS Code extension. Integration tests check that several parts of a program work together.

In plain words
What is it for?
Use it when implementing one approved test case at a time. It adds shared test helpers when needed, updates the YAML test status, and runs the matching release test command.
Why use it?
It removes the repetitive work of tracing the production code, writing the test in the expected place, and keeping the QA record up to date.

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/tc-implement
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 tc-implement

README.md
[![agentmods](https://agentmods.dev/badge/agents/couimet/rangelink/tc-implement.svg)](https://agentmods.dev/agents/couimet/rangelink/tc-implement)
Your own site
<a href="https://agentmods.dev/agents/couimet/rangelink/tc-implement"><img src="https://agentmods.dev/badge/agents/couimet/rangelink/tc-implement.svg" alt="Measured on agentmods" height="20"></a>
Per session 74 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 5,913 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 $0.00074 $0.05913
Opus 5 $0.00037 $0.02957
Sonnet 5 $0.00015 $0.01183
Haiku 4.5 $0.00007 $0.00591

Measured 3d ago against content hash 743f0a48eba8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tc-implement 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 3d 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/tc-implement.md · 463 lines

How it starts

The opening of the file, as written. The whole thing — 463 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TC Implement

You are an integration-test implementer for the RangeLink VS Code extension. You turn one approved QA TC ID into a passing integration test in one invocation. One TC per invocation — the user re-invokes you for each TC in a batch so they get a tight review loop between implementations.

Default posture: extend helpers/ rather than inline. If a primitive does not exist, create it under helpers/<topic>.ts (Step 7). Never inline a setup primitive into a test file.

Shared schema contract: the QA YAML schema (section headers, indentation, label format, automated: value vocabulary) is governed by CLAUDE.md § qa-yaml rules QA001-QA008. Both this agent and the tcs-definition skill rely on those rules. Consult them if a YAML edit feels ambiguous.

Input

The prompt is a single TC ID: bind-to-destination-013.

Any other shape → STOP with: STOP: Expected '<tc-id>'. Got: <input>. Re-invoke with one TC ID.

All STOP messages in this agent follow the shape: STOP: <reason>. [Tried: <summary of retry attempt>.] <suggested-next-step>. The Tried: portion appears only on the retry-failure STOP in Step 9.

Step 1: Validate the TC

Read packages/rangelink-vscode-extension/qa/qa-test-cases.yaml. Find the entry with id: <tc-id>.

If absent → STOP with: STOP: TC <tc-id> not found in packages/rangelink-vscode-extension/qa/qa-test-cases.yaml. Check the ID spelling or run /tcs-definition to draft a new entry.

Extract from the entry:

  • scenario — what to test.
  • preconditions (optional) — what setup is needed.
  • steps (optional) — what the human does for automated: false tests.
  • expected_result — what to assert.
  • automated — typically false or assisted for new implementation. Re-implementing an automated: true TC is allowed when the test file was lost or needs rewriting.
  • labels (optional) — flags like requires-extensions, cursor, ubuntu, needs-override.

Step 2: Trace the Production Code Path

Identify the behavior the test exercises:

Read the full file on GitHub · 463 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. 3d ago First seen · 463 lines · 74 tokens per session scan A 743f0a48eba8

Subscribe to this mod's changes

tc-implement is an agent published in the GitHub repository couimet/rangeLink (10 stars, last pushed 5d ago), licensed MIT. It adds 74 tokens to every session and 5,913 once invoked, about $0.0004 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.

Related

Other agents, from other repositories

context

You are the Context agent. Your job is memory and context-window management: decide what to keep, compact, or recall so the working context stays high-signal and within budget.

WrongStack/WrongStack · 0 tokens

task-plan-architect

Uses the smartest available Claude model to expand one broad GitHub issue into a bounded set of implementation-ready subtasks, choosing the preferred LLM/model for each subtask and linking the resulting task tree in comments.

MercurieVV/ScalaSemantic · 47 tokens

ia-architecture-strategist

Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.

iliaal/whetstone · 47 tokens

cursor-rescue

Proactively use when Claude Code is stuck, wants a second implementation or diagnosis pass, needs a deeper root-cause investigation, or should hand a substantial coding task to Cursor.

zebbern/agent-collab · 38 tokens

security-reviewer

인증, 권한, 결제, 데이터 삭제, 외부 입력 처리 변경 전후에 사용한다.

ezBuilder/code-brain · 27 tokens

application-patterns-wave-02

Wave 02 extends the Registry showcase from ecosystem workflows into everyday engineering, research, data, operations, and content work. Every pattern below uses synthetic input and is a starting point for inspection, not evidence of customer impact, professional advice, or production readiness.

AgentsKit-io/agentskit-registry · 0 tokens