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 xD4O/praxis --skill code-quality-analysisgit clone --depth 1 https://github.com/xD4O/praxisWrote 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/xd4o/praxis/code-quality-analysis)<a href="https://agentmods.dev/skills/xd4o/praxis/code-quality-analysis"><img src="https://agentmods.dev/badge/skills/xd4o/praxis/code-quality-analysis/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/xd4o/praxis/code-quality-analysis"><img src="https://agentmods.dev/badge/skills/xd4o/praxis/code-quality-analysis.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 | $0.01438 |
| Opus 5.5 | $0.00035 | $0.00575 |
| Sonnet 5.5 | $0.00017 | $0.00288 |
| Haiku 4.5 | $0.00009 | $0.00144 |
Grade A, and why
code-quality-analysis 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 15d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Quality Analysis Protocol
EXTREMELY_IMPORTANT: This is a MANDATORY protocol, not a suggestion. Follow every step. Do not skip steps. Do not combine steps. Do not summarize. Work through each gate in order.
Tests verify that code WORKS. This protocol verifies that code is WELL-DESIGNED. Run these checks on any significant code you write or review.
THE 15 CHECKS
Work through each. Mark PASS, FAIL, or N/A. Do not skip any applicable check.
Readability
1. NAMING — Does every variable, function, and class name reveal its intent?
processData()→ FAIL.extractValidEmails()→ PASS.- Booleans read as questions:
isValid,hasPermission,canExecute. - No abbreviations a new reader couldn't understand.
2. FUNCTION SIZE — Does every function do exactly one thing?
- Length is the smell: past ~20 lines a function has usually accreted a second job. Extract methods. (A long but irreducible unit — e.g. a flat dispatch table — can pass.)
- Can you describe what the function does without the word "and"?
3. NESTING DEPTH — Is anything nested deeper than 2 levels?
- Every nesting level is a condition the reader must hold in their head at once. Flatten with guard clauses. Return early for invalid cases.
- Happy path should be at indent level 1.
Structure
4. SINGLE RESPONSIBILITY — Does each module/class have exactly one reason to change?
- Can you describe it in one sentence without "and"?
- If it handles both parsing AND validation AND storage, split it.
5. COUPLING — Can you change module A without touching module B?
- Count the imports. More imports = more coupling.
- Are there method chains longer than 2 dots? Each extra dot couples this code to another object's internals (Law of Demeter).
6. COHESION — Is everything inside this module related to the same concern?
- Would removing any function make the module incomplete?
- Would any function be more at home in a different module?
Safety
7. FAIL FAST — Do errors surface immediately with clear messages?
- No empty catch blocks.
- No silently defaulting to zero/null/empty on bad input.
- Errors include context: what input, what state, what was expected.
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.
- 15d ago First seen · 138 lines · 87 tokens per session scan A 4bf3e1288cd6
code-quality-analysis is a skill published in the GitHub repository xD4O/praxis (28 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 1,438 once invoked, about $0.0003 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 2026-10-02.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…