# Agentic Coverage Report

> Read-only report of where the agent-generated tests (*.agentic.spec.ts, *AgenticTest.java, test_agentic_*.py, ...) stand — agent-tests-only coverage, goal MET/NOT MET from agentic-test-plan.md, and any failing agent tests. Use when asked how the agent tests are doing, what coverage the agent tests reach, or whether the recorded goal is met. Never creates, edits, or deletes files.

- **Type:** Skill
- **Install:** `agentstack add skill-jpbaking-agentic-tests-agentic-coverage-report`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [jpbaking](https://agentstack.voostack.com/s/jpbaking)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [jpbaking](https://github.com/jpbaking)
- **Source:** https://github.com/jpbaking/agentic-tests/tree/main/skills/shared/agentic-coverage-report

## Install

```sh
agentstack add skill-jpbaking-agentic-tests-agentic-coverage-report
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Agentic Coverage Report

Read-only: do NOT create, edit, or delete any test, source, config, or plan
file. Report and stop.

1. Read the `agentic-unit-test` skill's `SKILL.md` for the agent-test
   definitions, and `docs/coverage-recipes.md` next to it for the
   agent-tests-only coverage command. Both live in the sibling
   `agentic-unit-test` skill directory (`../agentic-unit-test/` relative to
   this file). If that skill is not installed, say so and STOP.
2. If no agent tests exist in the project, report "no agent tests found — use
   the `agentic-unit-test` skill to generate them" and STOP.
3. Run the agent-tests-only coverage command for this project's framework.
4. Print the `agentic-unit-test` skill's Step-5-style report:
   - **Goal**: read it from `agentic-test-plan.md` if that file exists (state
     MET / NOT MET); otherwise write "no goal on record".
   - **Coverage**: overall % and per-file table.
   - **Failing agent tests**: list any (or "none").

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [jpbaking](https://github.com/jpbaking)
- **Source:** [jpbaking/agentic-tests](https://github.com/jpbaking/agentic-tests)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-jpbaking-agentic-tests-agentic-coverage-report
- Seller: https://agentstack.voostack.com/s/jpbaking
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.