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.
npx skills add gpsaggese/helpers --skill testing.reach_coveragegit clone --depth 1 https://github.com/gpsaggese/helpersWrote 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.
[](https://agentmods.dev/skills/gpsaggese/helpers/testing.reach_coverage)<a href="https://agentmods.dev/skills/gpsaggese/helpers/testing.reach_coverage"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/testing.reach_coverage/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.
<a href="https://agentmods.dev/skills/gpsaggese/helpers/testing.reach_coverage"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/testing.reach_coverage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00013 | $0.00581 |
| Opus 5.5 | $0.00005 | $0.00232 |
| Sonnet 5.5 | $0.00003 | $0.00116 |
| Haiku 4.5 | $0.00001 | $0.00058 |
Grade A, and why
testing.reach_coverage 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
- Given the passed function, file, or files
<FILES>, raise unit test coverage in the test files<TEST_FILES>toward 100 percent, using a plan-then-implement approach
Workflow
Establish Current Coverage
-
Identify the test files for the target, using the rules
- E.g.,
helpers/hllm_cli.py -> helpers/test/test_hllm_cli.py
- E.g.,
-
Print the files to test
Target files: <FILES> Test files: <TEST_FILES> -
Run the command below and record the results:
# Using invoke (preferred): > i run_coverage --suite fast --generate-html-report # Or directly with pytest inside Docker: > pytest --cov=<PKG> --cov-report=term-missing --cov-report=html <TEST_FILE> -
Summarize which lines and branches are not covered
Design a Testing Plan
- Analyze the uncovered code paths and behaviors
- Propose a clear testing plan that:
- Tests functions modularly before testing interactions
- Prioritizes end-to-end and user-visible behavior over incidental implementation details
- Avoids testing assertions, defensive checks, or invalid inputs unless they are critical to correctness
- Explicitly map each uncovered area to one or more proposed tests
Specify Tests Without Implementation
- Define test classes and test method names
- For each proposed test:
- Describe the input data
- Describe the expected output or observable behavior
- Do not write executable test code at this stage
Implement After Approval
- Wait for user confirmation or feedback on the testing plan
- After approval:
- Implement the tests according to the approved plan
- Re-run coverage and verify that coverage for the target function is near 100 percent
- Report final coverage results and remaining gaps, if any
Important Rules
- Do not implement tests before the plan is approved
- Always adhere to the formatting and style guides referenced above
- Focus on meaningful behavior and correctness rather than superficial coverage
- All tests and code must strictly follow:
.claude/skills/coding.rules.mdfor any Python code.claude/skills/testing.rules.mdfor tests
- If any part of the task is unclear or underspecified, stop and ask for clarification before proceeding
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.
- yesterday First seen · 73 lines · 13 tokens per session scan A 331350007138
testing.reach_coverage is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 581 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 2026-11-06.
testing.reach_coverage compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| testing.reach_coveragegpsaggese/helpers | Skill | 158 | today | Apache-2.0 | A | 13 | Claude Code |
| test-masterJeffallan/claude-skills | Skill | 12k | 8d ago | MIT | A | 104 | Claude Code |
| migrate-xunit-to-xunit-v3dotnet/skills | Skill | 5.8k | today | MIT | A | 149 | Claude Code |
| go-testingGentleman-Programming/gentle-ai | Skill | 8.5k | today | MIT | A | 26 | Claude Code, Codex |
| principle-test-behavior-not-implementationmichael-denyer/pstack-claude | Skill | 4.1k | yesterday | MIT | A | 50 | Claude Code |
| dart-testdartsim/dart | Skill | 1.2k | today | BSD-2-Clause | A | 18 | Claude Code, Codex |
| test-generatorrshankras/claude-code-apple-skills | Skill | 867 | today | MIT | A | 33 | Claude Code |