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 KarhouTam/agent-skills --skill pytorch-test-refactoringgit clone --depth 1 https://github.com/KarhouTam/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/karhoutam/agent-skills/pytorch-test-refactoring)<a href="https://agentmods.dev/skills/karhoutam/agent-skills/pytorch-test-refactoring"><img src="https://agentmods.dev/badge/skills/karhoutam/agent-skills/pytorch-test-refactoring/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/karhoutam/agent-skills/pytorch-test-refactoring"><img src="https://agentmods.dev/badge/skills/karhoutam/agent-skills/pytorch-test-refactoring.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 | $0.00176 | $0.05411 |
| Opus 5 | $0.00088 | $0.02705 |
| Sonnet 5 | $0.00035 | $0.01082 |
| Haiku 4.5 | $0.00018 | $0.00541 |
Grade A, and why
pytorch-test-refactoring 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 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.
- .assets/diagrams/architecture.drawio 14 KB
- .assets/diagrams/architecture.svg 28 KB
- .assets/diagrams/decision-tree.drawio 12 KB
- .assets/diagrams/decision-tree.svg 36 KB
- .assets/diagrams/overview.drawio 9.9 KB
- .assets/diagrams/overview.svg 24 KB
- .assets/diagrams/signal-flow.drawio 17 KB
- .assets/diagrams/signal-flow.svg 51 KB
- .assets/diagrams/workflow.drawio 21 KB
- .assets/diagrams/workflow.svg 49 KB
- .gitignore 56 B
- agent/harness.py 3.4 KB runs code
- agent/harnesses/__init__.py 867 B runs code
- agent/harnesses/claude.py 7.2 KB runs code
- agent/harnesses/codex.py 7.2 KB runs code
- agent/prompts/analyst_baseline.md 1.5 KB
- agent/prompts/analyst.md 13 KB
- agent/prompts/checker_baseline.md 1016 B
- agent/prompts/checker.md 5.7 KB
- agent/prompts/coder_baseline.md 912 B
- agent/prompts/coder.md 16 KB
- agent/prompts/debugger.md 1.9 KB
- agent/prompts/feedback_analyst.md 2.0 KB
- agent/prompts/feedback_triage.md 2.1 KB
- agent/prompts/reviewer_batch.md 2.3 KB
- agent/prompts/reviewer.md 2.9 KB
- agent/skills/ci-automation/SKILL.md 3.8 KB
- agent/skills/refactor-test-decoupling/SKILL.md 22 KB
- agent/skills/review-test-refactoring/SKILL.md 25 KB
- agent/tasks.py 12 KB runs code
- AGENTS.md 9 B
- CHANGELOG.md 39 KB
- ci_ops.py 10 KB runs code
- CLAUDE.md 7.9 KB
- flow.py 46 KB runs code
- ingest_ops.py 6.0 KB runs code
- orchestrator.py 43 KB runs code
- README.md 30 KB
- reference/classification_guide.md 2.4 KB
- reference/device_api_catalog.yaml 27 KB
- reference/device_specific_features_report.md 2.2 KB
- reference/distributed/test_list.txt 14 KB
- reference/evaluation-guide.md 27 KB
- reference/graph/test_list.txt 20 KB
- review_ops.py 9.4 KB runs code
- scripts/assess.py 3.7 KB runs code
- scripts/ci.py 14 KB runs code
- scripts/ingest.py 10 KB runs code
- scripts/linter.py 20 KB runs code
- scripts/local_test.py 9.9 KB runs code
- scripts/logger.py 7.7 KB runs code
- scripts/report.py 4.0 KB runs code
- scripts/review_queue.py 13 KB runs code
- scripts/verify.py 45 KB runs code
- state.py 12 KB runs code
- tests/materials/analyst_report.json 9.3 KB
- tests/materials/analyst_report.md 9.3 KB
- tests/materials/analyst_result.json 84 B
- tests/materials/assessment.json 1.1 KB
- tests/materials/audit.jsonl 8.6 KB
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 · 406 lines · 176 tokens per session scan A a10bcceed127
pytorch-test-refactoring is a skill published in the GitHub repository KarhouTam/agent-skills (2 stars, last pushed 15d ago), with no licence file. It adds 176 tokens to every session and 5,411 once invoked, about $0.0009 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
readme-template
Standard README template for repos — professional structure with badges, overview, table of contents, features/modules, stack, installation, configuration, tests, security, structure, docs, roadmap, contribute, license, author + RepoActivity sections (Star History, repo stats) + profile GIF footer. Use when creating…
docker-single-port-multi-instance
Consolidate multiple Docker Compose app instances (production / test / demo) behind ONE host port using an nginx reverse proxy that routes by URL path prefix (e.g. /demo). Use when a user wants 'one port, several apps/banks' or a demo reachable simultaneously from the main landing page with its own database.
adhoc-verification
Produce fresh, focused, local verification evidence for a code change without relying on the full test suite. Use when a system reminder (or the user) demands ad-hoc verification after an edit, or when you want to prove one behavior in isolation. Covers the correct way to write a throwaway supertest/harness script…
agent-evaluation
This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", "implement LLM-as-judge", "compare model outputs", "mitigate evaluation bias", or mentions multi-dimensional evaluation, agent testing, quality gates, direct…
playwright-browser-automation
Run automated headless browser testing, scrape dynamic SPAs, capture high-resolution full-page screenshots, and perform visual regression testing with Playwright.
accessibility-testing-best-practices
Use when applying accessibility testing best practices.