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 atretyak1985/swarmery --skill code-standardsgit clone --depth 1 https://github.com/atretyak1985/swarmeryWrote 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/atretyak1985/swarmery/code-standards)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/code-standards"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/code-standards/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/atretyak1985/swarmery/code-standards"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/code-standards.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 | $0.00049 | $0.00958 |
| Opus 5.5 | $0.00020 | $0.00383 |
| Sonnet 5.5 | $0.00010 | $0.00192 |
| Haiku 4.5 | $0.00005 | $0.00096 |
Grade A, and why
code-standards 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 26d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Review code against the project's per-repository conventions and return a
violation report with file:line citations, severities, and before/after fixes.
Covers type safety (any detection, annotations), naming, Next.js 15 patterns,
Python typing and async style, service-config hygiene, and 12-factor
build-once/deploy-anywhere rules.
"Is this function too long or too complex?" → code-quality. "Does this use
any, follow naming, or comply with framework patterns?" → here.
Rules (never violate)
- Review only — never fix in place; fixes go to
@implementation-agent. - Every violation cites
file:lineand carries a severity; Critical and High findings include before/after code. NEXT_PUBLIC_*is allowed in source, prohibited as a Docker--build-arg.- Module-scope
process.env.Xis a violation; lazy access inside a function is not. - Never emit length, nesting, or complexity findings —
code-qualityowns those. - Close the report with the
STANDARDS-VIOLATIONS:trailer; cap it at 300 lines.
Resources
- Read
resources/review-procedure.mdbefore reviewing: the 8-step procedure, severity criteria, output template, self-check, escalation triggers, failure modes, and a worked example. - Read
resources/checklists.mdfor the rule set matchingrepo_type— web app, device/edge, service config, and the 12-factor build rules. - Read
resources/sandbox-preflight.mdwhen the run edits files from a git worktree isolate: one operation per Bash call, and the checks to make before the first read or write.
How to use
What it does
Checks code against your conventions and hands back an actionable report: type
safety including any types, naming, framework patterns, Python type hints and
async style, service-config hygiene, and 12-factor build rules — each finding
with a citation, a severity, and corrected code for the serious ones.
When to use it
- TypeScript/Next.js code changed and wants a standards pass before merge.
- Python device or edge code needs type hints and async patterns verified.
- A service config changed and needs lint, version bump, and template guards checked.
- A Dockerfile or CI pipeline changed and needs 12-factor compliance verified.
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.
- 26d ago Changed · +3 lines 735e1b8be34f
- 1mo ago First seen · 92 lines · 49 tokens per session scan A 16b99087165a
code-standards is a skill published in the GitHub repository atretyak1985/swarmery (7 stars, last pushed yesterday), licensed Apache-2.0. It adds 49 tokens to every session and 958 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
hone
Audit and improve an existing Quickstop plugin's quality against Claude Code plugin spec.
learn-from-sage
Detection-gap (miss) analysis for Code Review Sage. Learn from shipped fixes, acted-on human comments, and design outcomes to close reviewer blind spots. Inline during review stages a candidate; a human triggers a one-shot AI consolidation into the live ruleset.
code-standards
Code quality standards and style guide for reviewing pull requests.
manage-pull-requests
Manage Harness Code pull requests via MCP. List, create, update, and merge PRs; add reviewers and submit review decisions (approve / request changes); post, update, and delete comments; read the discussion timeline; and check CI status. Use when asked to open a PR, merge a PR, approve a PR, leave a code review…
sonarqube-mcp
Provides SonarQube and SonarCloud integration patterns via the Model Context Protocol (MCP) server. Enables quality gate monitoring, issue discovery and triaging, pre-push code analysis, and rule education directly in the agent workflow. Use when the user wants to check quality gates, search for Sonar issues, analyze…
audit
Repo audits, one mode or all (codebase, docs, process, perf, tests, threat-model, motion, SEO, debt). Triggers "audit the codebase", "full audit", "perf audit", "audit the tests", "threat model", "motion audit", "seo audit", "debt ledger".