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 machbuilds/atom --skill model-racegit clone --depth 1 https://github.com/machbuilds/atomWrote 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/machbuilds/atom/model-race)<a href="https://agentmods.dev/skills/machbuilds/atom/model-race"><img src="https://agentmods.dev/badge/skills/machbuilds/atom/model-race/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/machbuilds/atom/model-race"><img src="https://agentmods.dev/badge/skills/machbuilds/atom/model-race.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 | $0.00024 | $0.00483 |
| Opus 5.5 | $0.00010 | $0.00193 |
| Sonnet 5.5 | $0.00005 | $0.00097 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
model-race 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
model-race skill (Claude wrapper)
Source of truth: see the Tooling > model-race section of AGENTS.md
in this project. That file holds the canonical instructions every AI
tool reads.
This file is the Claude-specific wrapper. It exists so Claude Code's
Skill tool can register model-race as an invocable skill. Behavior
comes from AGENTS.md.
Quick reference
model-race start <feature> --spec <file> # create worktrees, write spec
model-race status # show race state
model-race launch <model> # open AI CLI in the model's worktree
model-race score # run automated scorecard
model-race judge # opt-in LLM evaluation
model-race merge <winner> # cherry-pick winner, clean losers
model-race abort # tear down (destructive)
model-race --help and model-race <command> --help show all flags.
When this skill activates (Claude-specific)
You should suggest model-race to the user only when:
- The user is about to make a non-obvious decision with multiple reasonable approaches (algorithm choice, API shape, refactor pattern).
- The work is high-stakes enough that the comparison cost is worth paying — typically anything that will be hard to change later.
- The user has not already chosen a path.
Do NOT suggest it for:
- CRUD endpoints, boilerplate, glue code.
- Anything where the answer is obvious.
- Bug fixes (these have one correct answer).
When the user races, the spec is critical
A race is only as good as its spec. Before model-race start, help the
user write a spec that:
- States the feature in one paragraph.
- Lists testable acceptance criteria (what makes it correct).
- Names constraints (perf budgets, API contracts, file boundaries).
- Excludes solution details (don't pre-decide the approach).
A weak spec produces three confused implementations and no clear winner. A strong spec produces three differentiated approaches you can actually compare.
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 · 59 lines · 24 tokens per session scan A e5fe4efebab4
model-race is a skill published in the GitHub repository machbuilds/atom (2 stars, last pushed 4mo ago), licensed MIT. It adds 24 tokens to every session and 483 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 skills, from other repositories
git-flow-pr
Executes the full PR-driven development workflow: create an isolated feature branch from the current work, commit all staged changes, rebase cleanly onto the selected base branch (skipping any ancestor commits already merged), push the branch, and open a GitHub pull request linked to a related issue. Includes guidance…
monorepo-management
Sets up or audits a monorepo workspace: tool selection, package naming, shared tooling, inter-package dependencies, selective CI, and versioning strategy. Invoked when the user asks to set up a monorepo, add a workspace, or manage multiple packages in a single repository.
new-gh-issue-orchestration
Orchestrates a GitHub-issue-driven delivery workflow from issue intake to PR creation using reviewer-first then worker execution. Invoked when the user provides a GitHub issue link/number and asks to start end-to-end delivery.
pull-request-automation
Audits and improves the pull request workflow for a GitHub repository. Covers PR description templates, auto-labelling, CODEOWNERS, PR size checks, and branch protection rules. Invoked when the user asks to improve the PR process, set up PR automation, or add a PR template.
git-worktree-workspaces
Sets up and uses Git worktrees for parallel task workspaces in the same repository clone, including safe cleanup of local worktrees. Invoked when the user asks to work on multiple branches at once, isolate tasks without extra clones, or create/remove worktrees.
write-changelog
Generates a CHANGELOG.md entry for a release by summarizing git commits since the last tag. Groups changes by type: Added, Changed, Fixed, Removed. Follows Keep a Changelog format (https://keepachangelog.com). Invoked when the user asks to update the changelog, write release notes, or prepare a release.