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 codecast-sh/codecast --skill cast-bakeoffgit clone --depth 1 https://github.com/codecast-sh/codecastWrote 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/codecast-sh/codecast/cast-bakeoff)<a href="https://agentmods.dev/skills/codecast-sh/codecast/cast-bakeoff"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-bakeoff/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/codecast-sh/codecast/cast-bakeoff"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-bakeoff.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 | $0.00084 | $0.00493 |
| Opus 5.5 | $0.00034 | $0.00197 |
| Sonnet 5.5 | $0.00017 | $0.00099 |
| Haiku 4.5 | $0.00008 | $0.00049 |
Grade A, and why
cast-bakeoff 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.
What it actually says
Arguing about two designs costs more than building both when each is under an hour. The branches share everything up to now and diverge only on the approach, so the comparison is fair.
Fork
Write each direction as a complete instruction for a thread that does not know it is one of several: the approach, the same acceptance criteria for all, and the same evidence to produce at the end (tests run, a screenshot, a short note on what was hard). Then one command:
cast fork --tip --label bakeoff-<topic> - - <<'EOF'
…approach one…
---
…approach two…
EOF
--tip keeps this whole thread in every branch. Each branch should stay in
its own worktree (cast ws acquire <name>) so the diffs do not collide.
Wait
cast sessions --label bakeoff-<topic> -w --json
The stream is silent until a branch changes state; run it in the background
and act on done and needs_input events. A branch that asks a question
gets the same answer every other branch would get, by cast send.
Compare
For each branch: cast diff <id> for size and files, cast read <id> for
the evidence and the note, and the time it took. Lay them out as a table:
approach, lines changed, files touched, tests passing, what was hard, and
the branch's short id. Then the verdict with the reason, and what the losing
branches found that the winner should adopt.
Hand the winner on: cast send <id> to continue it, or bring its diff into
this thread. Stash the others (cast stash <id>) and say which.
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 · 49 lines · 84 tokens per session scan A 239dea95d76a
cast-bakeoff is a skill published in the GitHub repository codecast-sh/codecast (40 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 493 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 2026-09-15.
Other skills, from other repositories
to-pr
Gate, push, and open a GitHub pull request on the repo's PR template, then watch CI.
deploy-check
MUST use before any git push to main/master/production, or when user mentions 'deploy', 'going live', 'push to prod', 'ready to ship', 'merge to main', 'release'. Also trigger before any npm publish for CLI tools, or on 'audit', 'check vulnerabilities', 'are our deps safe?', 'npm audit', 'yarn audit'. Performs: test…
changelog
Generate a changelog from git history since a tag, date, or commit.
pr-review
Review and post feedback on a GitHub or Gitea pull request end-to-end: fetch the PR diff, run a multi-agent code review, and auto-post the verdict as a real PR review (approve/request-changes/comment) via the platform's API. Triggers on: 'review this PR', 'review PR #N', 'check this pull request', 'post a PR review'…
github-project-management
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning.
agentic-jujutsu
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination.