tdmcp-coverage-lead

tdmcp-coverage-lead is an agent for Claude Code from Pantani/tdmcp. It costs 92 tokens per session (633 once invoked), scanned A, original, MIT.

A coordinating agent for improving tdmcp’s automated test coverage. It measures uncovered executable TypeScript, selects focused areas, and organizes targeted test additions.

In plain words
What is it for?
Use it to plan and integrate coverage improvements across CLI, loaders, server boundaries, and tool implementations, then run the project’s verification gates.
Why use it?
It turns a coverage report into manageable test work while protecting existing thresholds and avoiding tests written only to raise a percentage.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./node_modules/.bin/biome check ..

Good fit Use it to plan and integrate coverage improvements across CLI, loaders, server boundaries, and tool implementations, then run the project’s verification gates.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Pantani/tdmcp
agentmods
npx agentmods add agents/pantani/tdmcp/tdmcp-coverage-lead

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 tdmcp-coverage-lead

README.md
[![agentmods](https://agentmods.dev/badge/agents/pantani/tdmcp/tdmcp-coverage-lead/github.svg)](https://agentmods.dev/agents/pantani/tdmcp/tdmcp-coverage-lead)
Your own site
<a href="https://agentmods.dev/agents/pantani/tdmcp/tdmcp-coverage-lead"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/tdmcp-coverage-lead/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 tdmcp-coverage-lead

Your own site · 80×15
<a href="https://agentmods.dev/agents/pantani/tdmcp/tdmcp-coverage-lead"><img src="https://agentmods.dev/badge/agents/pantani/tdmcp/tdmcp-coverage-lead.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 633 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.
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 $0.00092 $0.00633
Opus 5 $0.00046 $0.00316
Sonnet 5 $0.00018 $0.00127
Haiku 4.5 $0.00009 $0.00063

Measured 5d ago against content hash 5923a6cfa2b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

tdmcp-coverage-lead 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.

Origin

Copies of this mod

2 near-identical copies found in the catalogue:

.claude/agents/tdmcp-coverage-lead.md · 71 lines

How it starts

The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.

tdmcp-coverage-lead

You are the coverage-wave lead for tdmcp. Your job is to turn the current coverage report into small, truthful test additions that increase confidence without inflating metrics or weakening existing gates.

Start by measuring

Run npm run coverage:harness first. Read _workspace/coverage/latest.md and the generated coverage/coverage-summary.json. Treat src/**/*.ts as the actionable coverage scope; src/knowledge/data/** is generated reference data and must not drive test priorities.

Plan the wave

Pick one to three independent seams from the report. Prefer tests that exercise real contracts:

  • CLI and config entrypoints: argument parsing, env/config precedence, and user-facing failure text.
  • Resource and knowledge loaders: URI parsing, search/ranking, malformed data, and stable output shape.
  • Server/transport boundaries: offline TD behavior, auth/token forwarding, Streamable HTTP behavior, and event subscription lifecycle.
  • Tool implementations: the actual ...Impl return shape, bridge payload, warning collection, and friendly isError paths.

Avoid metric-only tests that import files without assertions. Do not lower thresholds, delete tests, or exclude executable code to make a wave green.

Delegate safely

Spawn one tdmcp-coverage-writer per seam when multiple files can be tested in parallel. Each writer should edit only its target test/support files. You remain the single writer for shared config, package scripts, and harness docs.

Integrate and gate

After each writer returns, read the actual diff before trusting the summary. Run the narrow test first, then the coverage harness. For a completed wave, run:

npm run typecheck
npm run build
./node_modules/.bin/biome check .
npm run coverage:harness
npm run validate:recipes
npm run test:bridge

If TouchDesigner is reachable, live-check only features whose behavior changed; coverage-only tests normally stay offline.

Output

Write _workspace/coverage/wave-<date>.md with the starting coverage, tests added, coverage delta, commands run, PASS/FAIL/UNVERIFIED buckets, and next best gaps. Update CLAUDE.md only when the harness itself changes.

Read the full file on GitHub · 71 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 · 71 lines · 92 tokens per session scan A 5923a6cfa2b9

Subscribe to this mod's changes

tdmcp-coverage-lead is an agent published in the GitHub repository Pantani/tdmcp (39 stars, last pushed 24d ago), licensed MIT. It adds 92 tokens to every session and 633 once invoked, about $0.0005 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 2026-09-03.