Borrowing it
Nothing to install: this file belongs to nerds-odd-e/doughnut. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nerds-odd-e/doughnut/main/.agents/skills/dough-land/SKILL.mdgit clone --depth 1 https://github.com/nerds-odd-e/doughnutWrote 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/nerds-odd-e/doughnut/dough-land)<a href="https://agentmods.dev/skills/nerds-odd-e/doughnut/dough-land"><img src="https://agentmods.dev/badge/skills/nerds-odd-e/doughnut/dough-land/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/nerds-odd-e/doughnut/dough-land"><img src="https://agentmods.dev/badge/skills/nerds-odd-e/doughnut/dough-land.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 | $0.00194 | $0.02938 |
| Opus 5.5 | $0.00078 | $0.01175 |
| Sonnet 5.5 | $0.00039 | $0.00588 |
| Haiku 4.5 | $0.00019 | $0.00294 |
Grade A, and why
dough-land 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 yesterday.
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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dough Land
Land one reviewed checkout, an owned worktree or the default checkout on the
target branch: commit everything in it, publish that onto the authorized remote
trunk, refresh a supplied default checkout when safe, and retire an owned worktree
only after completion and retirement gates hold. Apply completion attention to the final
response. Publication, refresh, and cleanup are separate results.
A later step that stops or is deferred never undoes an earlier one.
With --process-retrospective, also
review this landing's process.
Run only when the developer explicitly invokes Dough Land, or when a calling skill's own validated keep instruction links here. An explicitly invoked findings-maintenance skill may instead supply its own validated maintenance instruction and link here; that instruction carries its maintenance-only publication authority without another keep question. It supplies the reviewed owned result, checkout, starting revision and authorized target, and confirms the whole-checkout isolation required below. This handoff neither invokes maintenance from encountering a finding nor authorizes unrelated work. Reviewing, approving, pausing, or saying "keep" in passing does not start a landing. Do not open a pull request, request a hosted merge, or discard anything; when the developer wants one of those, stop and say that Dough Land does not do it.
Resolve the checkout and target
Resolve both before any commit:
- Landing checkout. The checkout named by the invocation or its context: normally the current one, or the owned workspace a calling skill recorded. When the context says the change sits on the default checkout, that checkout is the one to land. Record its path and branch, whether this work created it or reused one another workflow owns, and its starting revision when known. Ownership comes from that context or the worktree's creation record; do not infer it from a clean directory. In an established session, the session's block names this checkout, its role, starting revision, and target.
- Default checkout. The project's established checkout for ordinary work, when the context supplies one; the refresh step inspects it. Landing needs no default checkout. When the landing checkout is a worktree, the default checkout is a different one; when the change sits on the default checkout, it is the landing checkout and needs no separate refresh source.
- Target. The authorized remote target as
refs/heads/<branch>on a named remote: the target selection already recorded for this worktree, or the one the project or developer authorizes. Default the branch tomainonly when neither the caller nor the project supplies one.
What ships with it
7 files 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.
- references/completion-attention.md 4.1 KB
- references/dashboard-completion.md 7.0 KB
- references/publish-reviewed-checkout.md 4.5 KB
- references/worktree-retirement.md 5.8 KB
- scripts/queued-closure-check.mjs 3.5 KB runs code
- scripts/retirement-checks.mjs 3.8 KB runs code
- scripts/worktree-retirement.mjs 6.7 KB runs code
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.
- yesterday Changed · +2 lines e12dbacb14f3
- 10d ago Changed · +6 lines · +5 tokens per session 065df02277ac
- 11d ago Changed · +38 lines · +24 tokens per session ded208c72b45
- 18d ago Changed · +2 lines 9167eb294841
- 19d ago Changed · -71 lines 8276b5a910e5
- 23d ago Changed · +14 lines · +27 tokens per session f27a0f1613fa
- 26d ago Changed · +18 lines c3fce4821ef2
- 27d ago Changed · +19 lines 547e0ad6c3d5
- 29d ago Changed · +16 lines · +16 tokens per session 53a539315b5b
- 1mo ago First seen · 207 lines · 122 tokens per session scan A 045f07d3756f
dough-land is a skill published in the GitHub repository nerds-odd-e/doughnut (50 stars, last pushed today), licensed MIT. It adds 194 tokens to every session and 2,938 once invoked, about $0.0008 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 2026-09-25.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage automatic Git syncing on macOS with repo-sync. Use only when the user explicitly invokes /repo-sync.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…