apply · localixai — Claude Code skill: what it does and how to install
apply is a Claude Code skill that applies a selected tokendoctor audit fix after showing the proposed edits. It is moving to /tokendoctor fix <id>, which runs without a model call.
MIT ★ 171 updated 2026-11-17
/plugin marketplace add localixai/tokendoctor
/plugin install tokendoctor@tokendoctorWhat apply does
The skill runs tokendoctor-apply for an audit finding. Its first pass lists the files and line changes without writing anything. The agent explains which settings scope will be affected, then waits for a clear confirmation.
After confirmation, the command writes the changes and backs up an existing file as .tokendoctor-<timestamp>.bak. It will not overwrite an existing agent file. Settings are not edited by hand; --write is used only after the dry run has been shown. This command is due to disappear in the next release.
What it helps with
- inspect proposed edits for an audit finding
- require approval before writing settings
- back up an existing file before changing it
Example prompts for the agent
- Show the tokendoctor fix for finding
finding-idand wait for my approval before writing it. - Apply the fix for
finding-idto project settings after showing the dry run. - List the files that would change for
finding-idwithout writing anything yet.
How to install apply
1Plugin marketplace
/plugin marketplace add localixai/tokendoctor/plugin install tokendoctor@tokendoctorThis installs the whole tokendoctor plugin with all its skills
2Skills CLI (Vercel)
npx skills add localixai/tokendoctor --skill apply -a claude-code3Manually: put the files in place
~/.claude/skills/apply/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/apply/
1Skills CLI (Vercel)
npx skills add localixai/tokendoctor --skill apply -a codex2Manually: put the files in place
.agents/skills/apply/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add localixai/tokendoctor --skill apply -a cursor2Manually: put the files in place
.cursor/skills/apply/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install localixai/tokendoctor skills/apply2Manually: put the files in place
.github/skills/apply/SKILL.md1Skills CLI (Vercel)
npx skills add localixai/tokendoctor --skill apply -a gemini-cli2Platform CLI
gemini skills install https://github.com/localixai/tokendoctor --path skills/applyManually: put the files in place
.devin/skills/apply/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about apply
How do I install apply in Claude Code?
Add the marketplace with /plugin marketplace add localixai/tokendoctor, then install the plugin with /plugin install tokendoctor@tokendoctor.
What does apply do?
It previews the changes for a tokendoctor audit finding, waits for explicit approval, then writes them. An existing file is backed up before the write.
What does apply need to run?
It needs the tokendoctor-apply command. The skill uses it to preview changes, then runs it with --write after approval.
Source text
SKILL.md · MIT
--- name: apply description: Apply one tokendoctor audit fix after showing the exact change. Moved to /tokendoctor fix <id>, which needs no model call. disable-model-invocation: true allowed-tools: Bash(tokendoctor-apply *) argument-hint: <finding-id> [--scope user|project|local] --- Apply the fix for the audit finding named in `$ARGUMENTS`. First say in one line that `/tokendoctor fix <id>` does the same with no model call and that this command goes away in the next release. 1. Run `tokendoctor-apply $ARGUMENTS` with no `--write`. It prints which files would change and a short -/+ summary, and changes nothing. 2. Show the user that output: the file path, the lines removed and added, and the scope (user settings affect every project; project settings are shared with the team through git; local settings are personal to this project). 3. Ask for confirmation. Do not proceed on silence or an unrelated reply. 4. After a clear yes, run the same command with `--write`. It copies an existing file to `<file>.tokendoctor-<timestamp>.bak` before writing, and never overwrites an existing agent file. 5. Report what was written and the backup path. Most settings apply to the running session, but say that a new session is the surest way to confirm, and that `/status` lists loaded files. Never edit settings files by hand from this skill, and never pass `--write` before the user has seen the dry run.
© rsaryev · MIT · localixai/tokendoctor
Similar skills
All skills for Agent setup: memory, context, orchestration →apply by other authors comes first.