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/format-changed/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/format-changed)<a href="https://agentmods.dev/skills/nerds-odd-e/doughnut/format-changed"><img src="https://agentmods.dev/badge/skills/nerds-odd-e/doughnut/format-changed.svg" alt="Measured on agentmods" 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 | $0.00042 | $0.00461 |
| Opus 5 | $0.00021 | $0.00230 |
| Sonnet 5 | $0.00008 | $0.00092 |
| Haiku 4.5 | $0.00004 | $0.00046 |
Grade A, and why
format-changed 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.
What it actually says
Format Changed
Format the current working-tree changes without taking ownership of Git state. The repository command owns changed-component detection; do not reproduce its path-to-component mapping in this skill or in ad hoc shell logic.
This is an explicitly on-demand skill. Routine execute-plan wrap-up runs the
same repository command directly and does not invoke this skill or spawn a
formatting agent.
Workflow
-
From the repository root, record
git status --shortso the final report can identify the changed paths present before formatting. -
Run the selective formatter through the repository runner:
./scripts/run.sh pnpm format:changedThe command considers staged, unstaged, and nonignored untracked paths and formats only their affected components.
-
If the command reports a mechanically determined correction that it could not apply, make only that mechanical correction and rerun the command. Examples include formatter-prescribed whitespace, import ordering, or another result with one unambiguous non-behavioral fix.
-
If resolving a result could change behavior, public types, architecture, or design intent, stop without guessing. Preserve any formatting already applied and report the diagnostic and the judgment needed.
-
Record
git status --shortagain and report every changed path remaining, including paths added or modified during formatting.
Never stage, commit, push, revert, restore, stash, or hide changes. Do not run
format:all, duplicate component detection, or broaden the task beyond
mechanical formatting results.
Handoff
On success, end the response with:
## FORMAT CHANGED COMPLETE
Include the command result and changed-path list immediately before the marker.
When judgment is required, include the failing diagnostic, changed-path list, and the decision needed, then end with:
## FORMAT CHANGED JIDOKA STOP
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 First seen · 62 lines · 42 tokens per session scan A 104f40213cd9
format-changed is a skill published in the GitHub repository nerds-odd-e/doughnut (49 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 461 once invoked, about $0.0002 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 2026-09-05.
Other skills, from other repositories
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
codex-autoresearch
Run autonomous, measurable experiments in a Git repository: change one hypothesis, verify a numeric metric, keep improvements, and revert failures. Use when the user wants Codex to keep iterating toward a numeric target in the foreground or as a detached background run. Do not use for ordinary one-shot coding…
changelog-composer
Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".