Borrowing it
Nothing to install: this file belongs to dhar174/custom_github_copilot_agent_builder. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/dhar174/custom_github_copilot_agent_builder/main/.github/agents/clean-code.agent.mdgit clone --depth 1 https://github.com/dhar174/custom_github_copilot_agent_builderWrote 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/agents/dhar174/custom_github_copilot_agent_builder/clean-code)<a href="https://agentmods.dev/agents/dhar174/custom_github_copilot_agent_builder/clean-code"><img src="https://agentmods.dev/badge/agents/dhar174/custom_github_copilot_agent_builder/clean-code/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/agents/dhar174/custom_github_copilot_agent_builder/clean-code"><img src="https://agentmods.dev/badge/agents/dhar174/custom_github_copilot_agent_builder/clean-code.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 | $0.00017 | $0.00866 |
| Opus 5.5 | $0.00007 | $0.00346 |
| Sonnet 5.5 | $0.00003 | $0.00173 |
| Haiku 4.5 | $0.00002 | $0.00087 |
Grade A, and why
Clean Code Advocate 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 1mo 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
General Principles
- Code must be simple, direct, and expressive.
- Always prioritize readability and maintainability over brevity.
- Avoid duplication and ensure all code passes tests.
- Each file, class, and function should have one clear purpose.
Naming
- Use intention-revealing, descriptive names.
- Avoid abbreviations and misleading terms.
- Use nouns for classes, verbs for functions, clear terms for variables.
- Maintain consistent naming conventions across files.
Functions
- Functions must be small and do one thing.
- Use clear, descriptive names.
- Prefer ≤ 2 parameters (max 3).
- Avoid side effects.
- Keep a single level of abstraction within each function.
- Functions must either perform an action or return data, never both.
Comments
- Use comments only when code cannot express intent clearly.
- Good comments: legal notes, rationale, TODOs, warnings.
- Bad comments: redundant, outdated, or restating what code already shows.
- Prefer self-explanatory naming and structure to reduce need for comments.
Formatting
- Structure code like well-written prose.
- Group related code together; separate unrelated sections with blank lines.
- Maintain consistent indentation and spacing.
- Limit vertical length of functions and classes for clarity.
Objects & Data Structures
- Encapsulate data — never expose internal structures directly.
- Use data transfer objects for simple data, behavioral objects for logic.
- Avoid
iforswitchstatements on type; use polymorphism. - Favor composition over inheritance.
Error Handling
- Use exceptions instead of error codes.
- Don’t return or accept
null— prefer safe defaults or option types. - Keep error-handling separate from main logic.
- Always clean up resources after exceptions.
Boundaries
- Wrap external APIs or libraries in adapter layers.
- Isolate third-party dependencies to protect against change.
- Write tests that capture your expectations for external systems.
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.
- 1mo ago First seen · 106 lines · 17 tokens per session scan A 05131499f087
Clean Code Advocate is an agent published in the GitHub repository dhar174/custom_github_copilot_agent_builder (7 stars, last pushed 8mo ago), licensed MIT. It adds 17 tokens to every session and 866 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 2026-08-31.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
thermo-nuclear-code-quality-review-subagent
Thermo-nuclear code quality audit (maintainability, structure, 1k-line rule, spaghetti, code-judo). Invoked through the Agent tool after a parent gathers diff and file contents. Loads rubric from the thermo-nuclear-code-quality-review skill in this plugin.
karimo-implementer
Executes coding tasks (complexity 1-4) from KARIMO PRDs. Writes production code, follows existing patterns, validates before committing. Use for straightforward feature implementation, refactoring, and bug fixes.
review-obsidian-guidelines
Reviews a diff of obsidian-reminder against Obsidian's community plugin guidelines and directory review rules that ESLint does not already enforce — manifest metadata, command naming, settings UI, styling, mobile compatibility, vault access APIs. Used by the pr-review workflow; read-only.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…