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 darrencroton/ai-agent-coder --skill style-guidegit clone --depth 1 https://github.com/darrencroton/ai-agent-coderWrote 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/darrencroton/ai-agent-coder/style-guide)<a href="https://agentmods.dev/skills/darrencroton/ai-agent-coder/style-guide"><img src="https://agentmods.dev/badge/skills/darrencroton/ai-agent-coder/style-guide/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/darrencroton/ai-agent-coder/style-guide"><img src="https://agentmods.dev/badge/skills/darrencroton/ai-agent-coder/style-guide.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 | $0.00094 | $0.02333 |
| Opus 5.5 | $0.00038 | $0.00933 |
| Sonnet 5.5 | $0.00019 | $0.00467 |
| Haiku 4.5 | $0.00009 | $0.00233 |
Grade A, and why
style-guide 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Style Guide
Three modes, sharing one standard:
draft— adapt references/baseline-style-guide.md into this project's ownSTYLE-GUIDE.md.audit— check written code against the project's drafted guide, or the baseline directly if none has been drafted.write— write or edit code following the project's drafted guide, or the baseline directly if none has been drafted.
A project's own drafted guide always wins over the baseline for anything it explicitly states. The baseline fills every gap the project hasn't decided for itself, and — before any guide is drafted — stands in for one entirely: audit and write always have a concrete standard to work from, even in a brand-new repository.
A drafted guide lives at the repository root as STYLE-GUIDE.md by default. If draft wrote it somewhere else, or the project already points to one from AGENTS.md/CLAUDE.md/CONTRIBUTING, audit and write use that location — check for an explicit pointer before assuming no guide exists and falling back to the baseline.
Boundaries
This skill stays in exactly one lane: naming, comments, documentation, logging/error presentation, metadata, tests, and generated-code handling.
- Mechanical formatting is the
lintskill's job, and the project's own formatter's job before that. Never restate a rule a linter or formatter config already enforces. - Quantitative structure — complexity, duplication, dependency shape — is
code-health's job. - Correctness, safety, and behavioural risk are
code-review's job. - A holistic pass that actually changes existing, working code is
code-simplifier's job;auditonly reports, andwriteonly applies the standard to code already being written for another reason — neither mode goes looking for unrelated code to change. - A written evidence synthesis for a stakeholder is the
reportskill's job.draftmode's output is a project artifact developers work from, not a report about one.
What ships with it
1 file 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.
- 1mo ago First seen · 109 lines · 94 tokens per session scan A bc71bfb25405
style-guide is a skill published in the GitHub repository darrencroton/ai-agent-coder (2 stars, last pushed 7d ago), licensed MIT. It adds 94 tokens to every session and 2,333 once invoked, about $0.0004 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 2026-09-08.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
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"…
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…
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…