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 vasilyu1983/AI-Agents-public --skill software-clean-code-standardgit clone --depth 1 https://github.com/vasilyu1983/AI-Agents-publicWrote 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/vasilyu1983/ai-agents-public/software-clean-code-standard)<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/software-clean-code-standard"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/software-clean-code-standard/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/vasilyu1983/ai-agents-public/software-clean-code-standard"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/software-clean-code-standard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.03395 |
| Opus 5 | $0.00018 | $0.01698 |
| Sonnet 5 | $0.00007 | $0.00679 |
| Haiku 4.5 | $0.00004 | $0.00340 |
Grade A, and why
software-clean-code-standard 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 9d 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 — 234 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Clean Code Standard
This skill is the authoritative clean code standard for this repository's shared skills. It defines stable rule IDs (CC-*), how to apply them in reviews, and how to extend them safely via language overlays and explicit exceptions.
Modern Best Practices: Prefer small, reviewable changes and durable change context. Use BCP 14 normative language consistently (RFC 2119 + RFC 8174). Treat security-by-design and secure defaults as baseline (OWASP Top Ten 2025, NIST SSDF). Prefer GitHub rulesets over branch-protection-only governance. Build observable systems with OpenTelemetry. For current tool choices, consult data/sources.json and prefer official docs first.
Judgment over dogma: This standard's CC-* rules are durable (coupling/cohesion, naming, small interfaces, explicit errors). Numeric folklore — hard function-length caps, "comments are a smell," DRY applied absolutely — is not. Robert C. Martin's Clean Code (2nd ed., 2025) and John Ousterhout's A Philosophy of Software Design disagree in a published, public debate on function size and commenting (see references/code-quality-operational-playbook.md § 14); apply the rule ID's intent, not a book's specific numeric prescription, and know when not to refactor (§ 14.3 of the same reference).
Quick Reference
| Task | Tool/Framework | Command | When to Use |
|---|---|---|---|
| Cite a standard | CC-* rule ID |
N/A | PR review comments, design discussions, postmortems |
| Categorize feedback | CC-NAM, CC-ERR, CC-SEC, etc. |
N/A | Keep feedback consistent without "style wars" |
| Add stack nuance | Language overlay | N/A | When the base rule is too generic for a language/framework |
| Allow an exception | Waiver record | N/A | When a rule must be violated with explicit risk |
| Reuse shared checklists | assets/checklists/ |
N/A | When you need product-agnostic review/release checklists |
| Reuse utility patterns | references/*-utilities.md |
N/A | When extracting shared auth/logging/errors/resilience/testing utilities |
What ships with it
37 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.
- agents/openai.yaml 329 B
- assets/checklists/backend-api-review-checklist.md 2.7 KB
- assets/checklists/frontend-performance-a11y-checklist.md 2.5 KB
- assets/checklists/mobile-release-checklist.md 4.3 KB
- assets/checklists/secure-code-review-checklist.md 2.6 KB
- assets/checklists/ux-design-review-checklist.md 2.4 KB
- assets/checklists/ux-research-plan-template.md 2.9 KB
- CONVENTIONS.md 11 KB
- data/sources.json 20 KB
- learnings.consolidated.md 604 B
- learnings.md 2.4 KB
- references/art-of-clean-code-operational-checklist.md 2.3 KB
- references/auth-utilities.md 20 KB
- references/clean-code-operational-checklist.md 3.2 KB
- references/clean-code-standard.md 12 KB
- references/clean-coder-operational-checklist.md 2.3 KB
- references/code-complete-operational-checklist.md 3.1 KB
- references/code-complexity-metrics.md 23 KB
- references/code-quality-operational-playbook.md 58 KB
- references/config-validation.md 21 KB
- references/design-patterns-operational-checklist.md 3.6 KB
- references/error-handling.md 26 KB
- references/functional-programming-patterns.md 20 KB
- references/llm-utilities.md 22 KB
- references/logging-utilities.md 19 KB
- references/observability-utilities.md 21 KB
- references/practice-of-programming-operational-checklist.md 2.0 KB
- references/pragmatic-programmer-operational-checklist.md 2.0 KB
- references/refactoring-operational-checklist.md 3.0 KB
- references/resilience-utilities.md 29 KB
- references/testing-utilities.md 19 KB
- references/utility-patterns.md 6.3 KB
- references/working-effectively-with-legacy-code-operational-checklist.md 1.9 KB
- skill-dependencies-schema.json 2.1 KB
- skill-dependencies.json 18 KB
- SKILL-TEMPLATE.md 3.8 KB
- sources-schema.json 4.7 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.
- 9d ago First seen · 234 lines · 37 tokens per session scan A 8d77cac6f68f
software-clean-code-standard is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (87 stars, last pushed 10d ago), licensed MIT. It adds 37 tokens to every session and 3,395 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
code-review-excellence
Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.
multi-reviewer-patterns
Coordinate parallel code reviews across multiple quality dimensions with finding deduplication, severity calibration, and consolidated reporting. Use this skill when organizing multi-reviewer code reviews, calibrating finding severity, or consolidating review results.
babysit
Watch an open PR — fix failing CI, handle the straightforward review comments, and drive it to a mergeable state. Claude Code analog of Cursor's built-in /babysit. Use after opening a PR when the user wants the agent to shepherd it without re-prompting.
make-pr-easy-to-review
Prepare PRs for review by cleaning noisy history, improving PR descriptions, and adding reviewer guidance without changing code behavior. Use for "make this easy to review", "tidy this PR", "clean up commits", or "annotate the diff".
spawn-reviewers
Spawn and collect the reviewer fleet at stage20spawnreviewers. Consumes spawn.json.spec (the authoritative spawn spec from derive-spawn-spec / derive-static-spec), resolves CODEINTELALLOWED, builds per-agent prompts from the per-agent template + role suffixes (Bug Hunter A/B, Unified Auditor, Domain Critics, Impact…
no-comments
Spawn the comment-sicko subagent, fix accepted findings, and offer encodings for claimed constraints.