Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.
Use this Skill: https://skilld.dev/gh/juliusbrussee/caveman/surgical-patch Nothing lands on disk. Nothing to clean up.
Edit a local copy. It keeps the author and licence.
≈45 tokens for metadata: the name and description. ≈115 when used: this file. ≈49 more on demand in 1 file.
Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.
In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈179 characters, or 2.2%.
The 1% threshold is a size suggestion. Longer descriptions can still fit.
Your model, settings, and other Skills decide how much text your Agent can read.
The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.
Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.
Reproduce failure first when economical; otherwise capture strongest available evidence.
Run focused proof plus nearest affected gate. Stop when failure is fixed and regression proof passes.
Source: SKILL.md on GitHub
No rule matched.
skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.
skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.
This skill provides a set of procedural instructions for a "surgical patch" debugging methodology. It contains no executable code, network operations, or external dependencies.
No alerts
Risk: LOW · No issues
Signed by skilld at bad48a0. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.
Last checked against GitHub last week.