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 Anselmoo/mcp-ai-agent-guidelines --skill fix-codecov-gapsgit clone --depth 1 https://github.com/Anselmoo/mcp-ai-agent-guidelinesWrote 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/anselmoo/mcp-ai-agent-guidelines/fix-codecov-gaps)<a href="https://agentmods.dev/skills/anselmoo/mcp-ai-agent-guidelines/fix-codecov-gaps"><img src="https://agentmods.dev/badge/skills/anselmoo/mcp-ai-agent-guidelines/fix-codecov-gaps/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/anselmoo/mcp-ai-agent-guidelines/fix-codecov-gaps"><img src="https://agentmods.dev/badge/skills/anselmoo/mcp-ai-agent-guidelines/fix-codecov-gaps.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 | $0.00087 | $0.01114 |
| Opus 5 | $0.00044 | $0.00557 |
| Sonnet 5 | $0.00017 | $0.00223 |
| Haiku 4.5 | $0.00009 | $0.00111 |
Grade A, and why
fix-codecov-gaps 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fix Codecov Coverage Gaps
Restores or improves patch coverage after Codecov flags missing/partial lines in a pull request.
When to Use
- Codecov bot posts a report showing patch coverage below the project baseline
- A PR introduces new lines without accompanying tests
- Coverage regresses (Misses or Partials increase vs. base)
Procedure
1. Fetch the Codecov Report
Use mcp_github_pull_request_read with method: get_comments to read PR comments, then locate the comment from codecov[bot]. Extract:
- Patch coverage % (overall for this PR's changed lines)
- Files with missing lines — collect the file path, patch %, missing count, and partial count for each row in the table
- Coverage diff summary — Hits Δ, Misses Δ, Partials Δ vs. base
Example output to parse:
| src/cli.ts | 80.30% | 12 Missing + 1 partial |
| src/onboarding/wizard.ts | 83.33% | 0 Missing + 5 partials |
2. Identify Uncovered Lines Per File
For each file listed in the Codecov report:
- Open the file and read its contents
- Cross-reference the diff (
mcp_github_pull_request_readwithmethod: get_diff) to pinpoint which new/changed lines are uncovered - Classify each gap:
- Missing line — the line was never executed in any test
- Partial branch — the line ran but not all branches (e.g. both sides of a ternary or
??)
Priority order: tackle files with the most missing lines first. Partials are secondary.
3. Write Targeted Tests
For each uncovered line or partial branch, add or extend a test in src/tests/<mirrored-path>/<module>.test.ts:
- Missing line (error path / guard clause): Write a test that triggers the error condition or the early-return branch
- Missing line (happy path): Write a test that calls the function with valid input that exercises that code path
- Partial branch (ternary /
??/&&): Add a test case that exercises the other side of the branch
Rules:
- Mirror the source tree:
src/cli.ts→src/tests/cli/cli.test.ts - Use
vi.fn()/vi.spyOn()for side effects; never mutate module state across tests - Each new
it()block must contain at least oneexpect() - Do not use
/* c8 ignore */to hide the gap — fix the root cause
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.
- 10d ago First seen · 112 lines · 87 tokens per session scan A 54bcffd37b72
fix-codecov-gaps is a skill published in the GitHub repository Anselmoo/mcp-ai-agent-guidelines (6 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 1,114 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.
Other skills, from other repositories
tests-run
Execute Unity tests (EditMode or PlayMode) and return per-test results. Supports filtering by test assembly, namespace, class, and method. Refreshes the AssetDatabase first; defers execution across domain reloads if scripts changed. Precondition: every open scene must be saved — dirty scenes abort the run.
testing-assistant
Manages testing lifecycle including unit tests, integration tests, validation, and quality assurance.
testing
To write thorough, isolated, idempotent tests — 80%+ coverage, external-only mocking, scenario-driven.
write-unit-tests
Write comprehensive unit tests with proper setup, assertions, and coverage of happy paths, edge cases, and error scenarios.
edt-mcp-project-yaxunit
Discover, run, debug, poll, and cancel YAXUnit tests through current EDT-MCP launch and background-job contracts. Not for generic UI tests.
unit-testing
Writes unit tests for code that already exists — choosing what deserves a test, what the cases are, and how to assert without welding the test to the implementation. Use this whenever the user asks for tests, unit tests, more coverage, or tests for a specific function or module, and also when adding to untested code…