Skills

Patcher Overview

Stage 4 patch generation playbook.

Install

npx skills add BitterSecurity/Decepticon --skill patcher-overview -g -a claude-code -y
Category
AI and agents
Updated
3d ago
License
Apache-2.0
Context cost
Lightabout 640 tokens
Runs scripts
No, instructions only

What it does

Stage 4 patch generation playbook. Minimal diffs for validated findings with mandatory patch_verify. Load at patcher-agent startup.

Patcher Skill

You fix validated findings and prove the fix holds. Minimal diffs, one concern at a time, mandatory patch_verify before claiming done.

Iteration loop

while not patched and attempts < 3:
    1. kg_query(kind="vulnerability", min_severity="medium")
       → pick validated=True, patched!=True
    2. Read the function around (file, line)
    3. Design minimal fix (validate / escape / parameterize / safe API)
    4. patch_propose(vuln_id, diff, commit_message) → patch_id
    5. Apply diff via Edit or bash patch
    6. (optional) bash: run repo tests, abort on failure
    7. patch_verify(patch_id, poc_command, success_patterns,
                    test_cmd=optional)
    8. if status == "verified": done
       elif status == "tests_failed": revert, retry
       elif status == "regressed": revert, analyze, retry
    attempts += 1

Diff style

  • Unified diff. Use git diff --no-color output or write one by hand.
  • Minimal hunk. One concern. No formatting. No renames. No "while I'm here" cleanups. No new files (unless adding one regression test).
  • Safe-API preference.
Bug classPreferred fix
SQL injectionParameterized query / ORM.filter(), NOT escaping
Command injectionArg-list subprocess, shell=False
Path traversalos.path.realpath + prefix check
SSRFAllowlist + resolve → check not private/loopback
DeserializationSwitch to safe loader (yaml.safe_load, JSON, etc.)
Broken authMove check to pre-hook, not inside handler
Reflected XSSFramework auto-escape, remove Markup/safe
Read the whole SKILL.md on GitHub

More in AI and agents