# Patch

Generate candidate fixes for verified security findings.

- Repository: https://github.com/anthropics/defending-code-reference-harness (7690 stars)
- Category: Security
- License: see repository
- Last updated: 2026-08-06
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add anthropics/defending-code-reference-harness --skill patch -g -a claude-code -y`
Codex: `npx skills add anthropics/defending-code-reference-harness --skill patch -g -a codex -y`
Cursor: `npx skills add anthropics/defending-code-reference-harness --skill patch -g -a cursor -y`
Gemini CLI: `npx skills add anthropics/defending-code-reference-harness --skill patch -g -a gemini-cli -y`

## Description

Generate candidate fixes for verified security findings. Consumes TRIAGE.json (preferred), VULN-FINDINGS.json, INCIDENTS.json, or a vuln-pipeline results directory. Pipeline input is delegated to the execution-verified `vuln-pipeline patch` ladder; static-analysis input gets a per-finding patch subagent + independent reviewer and is written as inert diffs for human review. Writes PATCHES/bug_NN/{patch.diff,patch_result.json}, PATCHES.md, and PATCHES.json. Use when asked to "fix the findings", "patch these vulns", "generate fixes", or "close the loop on triage".

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# patch

Third leg of the static pipeline (`/vuln-scan` → `/triage` → `/patch`).
Turns a ranked list of verified findings into candidate diffs.

The skill **never applies a diff** to the target repo. Output is inert text
in `./PATCHES/` for a human to review and apply out-of-band, see
`docs/patching.md#reviewing-generated-patches`. There is no `--apply` or
`--approve` flag by design: the capability isn't present, so it can't be
prompt-injected into use.

Invoke with `/patch <findings-path> [--repo PATH] [--top N] [--id fNNN]
[--model M] [--fresh]`.

**Arguments** (parse from `$ARGUMENTS`):
- findings path (first positional, required): `TRIAGE.json`,
  `VULN-FINDINGS.json`, a pipeline `results/<target>/<ts>/` directory, or any
  JSON the `/triage` ingest table recognizes.
- `--repo PATH`: target codebase, read-only (default cwd). Required for
  static mode; the skill stops if cited files don't resolve under it.
- `--top N`: patch only the N highest-severity true positives (static mode).
- `--id fNNN`: patch only the finding with this id.
- `--model M`: passed through to `vuln-pipeline patch` in execution-verified
  mode. Ignored in static mode (subagents inherit the orchestrator's model).
- `--fresh`: ignore `./.patch-state/` checkpoint and start over.

**Tools.** Prefer Read, Glob, Grep, Write, Task. Some sessions do not
provision Glob or Grep; `allowed-tools` is a permission filter, not a loader.
When they are unavailable, fall back to the read-only Bash commands
whitelisted above: `rg`/`grep` for search, `ls` for enumeration,
`head`/`file`/`wc` for sniffing, `jq` for JSON ingest. Bash is otherwise
permitted only for `python3 .claude/skills/_lib/checkpoint.py` (state I/O)
and `vuln-pipeline patch` (execution-verified delegate). `find` is NOT
permitted.

The rest: https://github.com/anthropics/defending-code-reference-harness/blob/HEAD/.claude/skills/patch/SKILL.md