A review step for checking whether recent code changes have enough automated tests. Test coverage means how much of the changed behavior is checked by tests.

It checks changed files, matching tests, uncovered branches, high-risk modules, and whether rendering changes may require updated snapshot tests.

It helps find changed code paths without tests and points out places where a later change could cause a regression, meaning an old behavior stops working.

How CsabaKovacs/rulesmith configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to CsabaKovacs/rulesmith. 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/CsabaKovacs/rulesmith/main/.agents/skills/test-guard/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/CsabaKovacs/rulesmith

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/csabakovacs/rulesmith/test-guard/github.svg)](https://agentmods.dev/skills/csabakovacs/rulesmith/test-guard)

Your own site

<a href="https://agentmods.dev/skills/csabakovacs/rulesmith/test-guard"><img src="https://agentmods.dev/badge/skills/csabakovacs/rulesmith/test-guard/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/csabakovacs/rulesmith/test-guard"><img src="https://agentmods.dev/badge/skills/csabakovacs/rulesmith/test-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 601 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.

Model	Per session	Once invoked
Fable 5.1	$0.00031	$0.00601
Opus 5.5	$0.00012	$0.00240
Sonnet 5.5	$0.00006	$0.00120
Haiku 4.5	$0.00003	$0.00060

Measured 1mo ago against content hash 0fc312e6c47c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

test-guard 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 1mo 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.

.agents/skills/test-guard/SKILL.md · 67 lines

How it starts

The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Test Guard

Evaluates test coverage for recent changes, identifies missing tests, and flags regression risks.

When to Activate

After ANY code modification that changes application logic, adds features, or modifies public interfaces.
Skip for documentation-only, style-only, or config-only changes that do not affect runtime behavior.

Evaluation Methodology

Follow these steps in order:

Identify all changed files and the nature of each change (new feature, bug fix, refactor, API change).
For each changed module, check if corresponding test files exist in packages/core/test/. (evidence: packages/core/test/)
Evaluate whether existing tests cover the changed code paths.
Flag missing test coverage: new public functions without tests, changed branches without assertions.
Assess regression risk: changes to safe.ts, render pipeline, or scanner are high-risk.
Test command: pnpm -r test (vitest). (evidence: package.json)
Test naming: <module>.test.ts matching source module. (evidence: packages/core/test/dtree.test.ts)
Snapshot tests for render output — flag if render changes may break snapshots. (evidence: packages/core/test/snapshots/)
Classify findings as: missing (no test exists), incomplete (test exists but doesn't cover change), regression-risk (existing test may break).
Report ONLY when gaps are found — produce no output if coverage is adequate.

Stack-Specific Test Rules

Check for vitest test files matching changed modules. (evidence: packages/core/test/)
Exported function signature changes require corresponding test updates.
Render changes should check snapshot impacts. (evidence: packages/core/test/snapshots/)
safe.ts changes are high-risk security boundary. (evidence: packages/core/test/fs.safe.test.ts)

Test Command

pnpm -r test

Boundaries

Do NOT write tests — only identify gaps and recommend what should be tested.
Do NOT flag missing tests for trivial getters, configuration, or generated code.
Do NOT require 100% coverage — focus on behavioral contracts and high-risk paths.
Focus on the changed code, not pre-existing coverage gaps.

Read the full file on GitHub · 67 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.

1mo ago First seen · 67 lines · 31 tokens per session scan A 0fc312e6c47c

Subscribe to this mod's changes

test-guard is a skill published in the GitHub repository CsabaKovacs/rulesmith (15 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 31 tokens to every session and 601 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

rulesmith: Skill for Claude Code