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 bestdeejay-design/agent-skills --skill coverage-analyzergit clone --depth 1 https://github.com/bestdeejay-design/agent-skillsWrote 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/bestdeejay-design/agent-skills/coverage-analyzer)<a href="https://agentmods.dev/skills/bestdeejay-design/agent-skills/coverage-analyzer"><img src="https://agentmods.dev/badge/skills/bestdeejay-design/agent-skills/coverage-analyzer.svg" alt="Measured on agentmods" 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 | $0.00078 | $0.01802 |
| Opus 5 | $0.00039 | $0.00901 |
| Sonnet 5 | $0.00016 | $0.00360 |
| Haiku 4.5 | $0.00008 | $0.00180 |
Grade A, and why
coverage-analyzer 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 7d 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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coverage Analyzer — coverage.py XML → readable analysis
Load this skill when you need to turn a coverage.xml report into a
human-readable coverage analysis: overall line/branch percent, files with
zero coverage, the 10 worst-covered files, a delta vs a previously stored
baseline, and a PASS/FAIL verdict against a threshold for CI.
The analyzer is pure Python 3 stdlib (xml.etree.ElementTree, json,
argparse) — no dependencies, no network. It reads the exact XML format that
coverage.py emits via coverage xml
(Cobertura-style DTD), so it works with any tool that produces that format
(pytest-cov --cov-report=xml, coverage run -m pytest && coverage xml).
The analyzer script
scripts/coverage_analyzer.py — pure Python 3 stdlib (no dependencies).
| Mode | Command |
|---|---|
| Basic analysis | python3 coverage_analyzer.py --xml coverage.xml |
| Delta vs stored baseline | python3 coverage_analyzer.py --xml coverage.xml --baseline baseline.json |
| Threshold gate (CI) | python3 coverage_analyzer.py --xml coverage.xml --threshold 80 |
| Store current totals as baseline | python3 coverage_analyzer.py --xml coverage.xml --save-baseline baseline.json |
Output sections
- Total —
line-rate(andbranch-ratewhen branches were actually measured; abranch-rate="0"withbranches-valid="0"is treated as "not measured", not as 0%), file count,files_with_zero_lines(files with line-rate == 0) with their names - Worst 10 files — lowest line-rate first, ascending
- Delta vs baseline — per-file
before → after → Δtable plus atotalrow; files absent from the baseline are markednew - Verdict —
PASS/FAILwhen--thresholdis given
Exit codes
| Code | Meaning |
|---|---|
0 |
analysis succeeded (threshold PASS, or no threshold) |
1 |
parse/read error, or threshold FAIL |
2 |
internal error |
Usage example (typical)
# 1. Produce the XML (coverage.py installed):
coverage run -m pytest && coverage xml
# 2. Analyze:
python3 coverage_analyzer.py --xml coverage.xml
# 3. Store a baseline on the first run:
python3 coverage_analyzer.py --xml coverage.xml --save-baseline baseline.json
# 4. On later runs, diff against the baseline and gate CI:
python3 coverage_analyzer.py --xml coverage.xml --baseline baseline.json --threshold 80
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 162 lines · 78 tokens per session scan A 4bf92e9f92e2
coverage-analyzer is a skill published in the GitHub repository bestdeejay-design/agent-skills (5 stars, last pushed 2d ago), licensed MIT. It adds 78 tokens to every session and 1,802 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
armada-verification
Mandatory pre-completion verification and evidence checklist before reporting done.
browser-use
Direct browser control via CDP for web interaction: automation, scraping, testing, screenshots, and site/app work.
benchmark-workflow
Run, diagnose, or change Xberg extraction benchmarks, quality scoring, benchmark fixtures, artifact contracts, and independently sourced ground truth. Load for the Benchmarks workflow or benchmark-harness work, not ordinary unit tests.
config-evals
Builds and maintains configuration-based evaluations on a workflow with the eval-config tool. Use when the user asks to set up, add, view, change, or remove an evaluation, score, grade, or judge a workflow's output, or measure answer quality against a test dataset. This is the only eval form Instance AI handles — it…
workflow
Use when a task is too large for turn-by-turn orchestration and should run through the big-task workflow lane: system-wide changes, large migrations, repo-wide audits, high-confidence verification, or tasks explicitly asking to run a workflow. Claude Code uses native dynamic workflows; Codex, OpenCode, and Grok use…
skill-compiler
Automatic solved-to-skill compiler — detects novel task completions and autonomously drafts new SKILL.md files. Stolen from Hermes Agent's learning loop (NousResearch, 2026-05-11).