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.
git clone --depth 1 https://github.com/cveralyon/axel-setupWrote 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/commands/cveralyon/axel-setup/style)<a href="https://agentmods.dev/commands/cveralyon/axel-setup/style"><img src="https://agentmods.dev/badge/commands/cveralyon/axel-setup/style/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/commands/cveralyon/axel-setup/style"><img src="https://agentmods.dev/badge/commands/cveralyon/axel-setup/style.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 | $0.00010 | $0.00742 |
| Opus 5.5 | $0.00004 | $0.00297 |
| Sonnet 5.5 | $0.00002 | $0.00148 |
| Haiku 4.5 | $0.00001 | $0.00074 |
Grade A, and why
style 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Switch response style based on the argument provided. Apply the selected style for the remainder of this session until the user switches again.
Available styles
concise (default)
- Short, direct answers. No preamble, no trailing summaries.
- Lead with the action or answer, not the reasoning.
- Code-heavy, explanation-light.
- This is the baseline defined in CLAUDE.md.
debug
- Verbose, investigative mode. Think out loud.
- Show your reasoning chain: what you checked, what you ruled out, why.
- Include line numbers, stack traces, and intermediate findings.
- Explain cause-and-effect clearly.
- Useful for: debugging sessions, incident investigation, root cause analysis.
teach
- Explain like a senior engineer mentoring a mid-level.
- Connect new concepts to things the user already knows (Ruby/Rails, Python, TS).
- Use analogies and concrete examples.
- After explaining, give the practical "how to apply this" takeaway.
- Useful for: learning new libraries, understanding unfamiliar codebases, architecture discussions.
architect
- Think in systems, not files. Start with the big picture.
- Evaluate trade-offs explicitly: performance vs maintainability, speed vs correctness.
- Reference industry patterns (CQRS, event sourcing, hexagonal, etc.) when relevant.
- Produce structured decision records: Context → Options → Decision → Consequences.
- Useful for: design discussions, API design, refactoring strategy, database schema decisions.
review
- Act as a critical code reviewer.
- Flag: bugs, security issues, edge cases, missing tests, CLAUDE.md violations.
- Score confidence (0-100) for each finding, only report 70+.
- Be brief per finding but thorough in coverage.
- Useful for: pre-commit review, PR review, pre-deploy checks.
ship
- Maximum speed, minimum ceremony.
- Don't explain decisions — just make them.
- Don't ask questions — use best judgment.
- Don't suggest alternatives — pick one and go.
- Only output code and the minimal context needed to understand it.
- Useful for: rapid prototyping, batch implementation, known patterns.
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 · 69 lines · 10 tokens per session scan A 83e373af6b98
style is a command published in the GitHub repository cveralyon/axel-setup (4 stars, last pushed 3mo ago), licensed MIT. It adds 10 tokens to every session and 742 once invoked, about $0.0000 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 commands, from other repositories
release
Run the weekly release checklist (triage, CHANGELOG, semver tag, GitHub Release, dev.to, LinkedIn, ufawkes.dev) and file the post-release DORA issue.
measure
Monthly DORA metrics snapshot from uFawkesObs, with anomaly flags and a post-release tracking issue.
oc-health
Verify OpenCode configuration, pinned agent models, determinism, and provider health.
plan
Research and produce intent.md, spec.md, and plan.md for a feature.
review-agents
Request focused code review from a subagent with git SHA context.
implement
Execute the plan.md with verification checkpoints.