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 CoriChui/yolo --skill yolo-finishgit clone --depth 1 https://github.com/CoriChui/yoloWrote 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/corichui/yolo/yolo-finish)<a href="https://agentmods.dev/skills/corichui/yolo/yolo-finish"><img src="https://agentmods.dev/badge/skills/corichui/yolo/yolo-finish/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/corichui/yolo/yolo-finish"><img src="https://agentmods.dev/badge/skills/corichui/yolo/yolo-finish.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 | $0.00082 | $0.01773 |
| Opus 5 | $0.00041 | $0.00886 |
| Sonnet 5 | $0.00016 | $0.00355 |
| Haiku 4.5 | $0.00008 | $0.00177 |
Grade A, and why
yolo-finish 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 9d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
yolo-finish
Land verified work. Match the rigor to the risk.
Precondition
The branch carries YOLO-Verified: true (.claude/yolo/conventions.md). If not, run yolo-verify first.
Run finish reasoning (risk classification, summary synthesis) at the agents.finish tier
from workspace/config.yaml (inherit if unset).
Choose the path (read workspace/config.yaml finish.mode)
- fast-local (
mode: local, or user says throwaway/offline): land with a real merge commit — always--no-ffso there is a commit to carry the done-trailer (never a fast-forward). Normal single-checkout case:git switch <base_branch> && git merge --no-ff feature/<slug> -m "yolo: merge feature/<slug>" -m "YOLO-Feature: <slug>". Ifbase_branchis checked out in another worktree, run that same merge from that worktree (git refuses to update a ref checked out elsewhere — don't fight it). The condensed summary goes in the merge-commit message. No forge. - PR (
mode: pr, the default): push the branch and open a PR/MR (gh pr create/glab mr create). The PR description IS the summary — generated from the brief (what) + plan (how) + diff (the work) + verification (evidence) — with theYOLO-Feature: <slug>trailer kept as the body's final standalone paragraph (see Land).
In BOTH paths the landing MUST produce the durable done-markers (see Land).
CI check (PR path; finish.ci)
"Has CI" means a required check actually reports on the PR (gh pr checks <pr> returns
checks / GitLab has a pipeline for the MR) — NOT merely the presence of a workflow file,
which may produce no required check.
auto: if a check reports, require it green before merge; if none reports, fall back to the yolo-verify result as the gate.require: always demand green CI. If NO check reports, this is a hard error — surface it to the human (do not wait forever on a check that will never arrive).off: never wait on CI. When polling a pending check, bound the wait (cap attempts / total time, e.g. ~20 min); on timeout, stop and escalate to the human rather than hanging.
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.
- 9d ago First seen · 104 lines · 82 tokens per session scan A fd1907abc5f3
yolo-finish is a skill published in the GitHub repository CoriChui/yolo (9 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 1,773 once invoked, about $0.0004 per session on Opus 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
pipeline-digest
Daily release-pipeline digest with a change gate — reports which plugins are pending release, whether main's CI is green, and which branches went stale, and notifies the operator only when that state actually moved since the last run. Use when the operator asks "what moved in the pipeline", "anything to ship"…
land-and-deploy
Merge PR, wait for CI, verify deploy, run canary. The complete landing pipeline.
release
Prepare a version release — bump version files, commit, and tag. Just run /release with no arguments.
release-plugin
Cut a cairn plugin release for a given MAJOR.MINOR.PATCH version, running every pre-flight and version gate before anything is changed or published.
release-init
Detect project type and generate a tailored project-level /release skill. Run once per project to set up releasing.
id-rollback
The infra-delivery INCIDENT safe-revert PROCEDURE skill (the recurring/incident rollback step) — the PROCEDURE the generic agent runs when a delivered change did NOT land (a NOT-LANDED realization, an escaped defect, bad config) to restore the last-known-good IaC and prove reality matches it again. The shape is git…