warden-sweep — Claude Code skill: what it does, how to install
warden-sweep scans an entire repository with Warden, verifies findings through tracing, and opens draft PRs for validated bugs.
Apache-2.0 302 installs ★ 426 updated 2026-10-24
npx skills add getsentry/warden --skill warden-sweep -a claude-codeWhat warden-sweep does
This skill runs a structured five-phase audit: full codebase scanning via Warden, deep tracing verification, GitHub tracking issue setup, sequential patch generation with draft PRs, and a markdown summary. All artifacts and intermediate data land in .warden/sweeps/<run-id>/.
The workflow depends on five command-line tools: warden, gh, git, jq, and uv. Without every single one installed in your environment, the underlying helper scripts immediately fail.
Patches are created sequentially on branches derived from the default branch, cleaning up each git worktree as it finishes. When a run gets interrupted, the skill inspects existing run artifacts and resumes from the first incomplete phase.
What it helps with
- scan an entire codebase with Warden
- verify security findings before writing code fixes
- open draft pull requests for verified bugs
- resume interrupted security audits without duplicated work
Example prompts for the agent
- Run a full repository sweep with Warden
- Scan everything, verify bugs, and create draft PRs for confirmed issues
How to install warden-sweep
1Skills CLI (Vercel)
npx skills add getsentry/warden --skill warden-sweep -a claude-code2Manually: put the files in place
~/.claude/skills/warden-sweep/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/warden-sweep/
1Skills CLI (Vercel)
npx skills add getsentry/warden --skill warden-sweep -a codex2Manually: put the files in place
.agents/skills/warden-sweep/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add getsentry/warden --skill warden-sweep -a cursor2Manually: put the files in place
.cursor/skills/warden-sweep/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install getsentry/warden skills/warden-sweep2Manually: put the files in place
.github/skills/warden-sweep/SKILL.md1Skills CLI (Vercel)
npx skills add getsentry/warden --skill warden-sweep -a gemini-cli2Platform CLI
gemini skills install https://github.com/getsentry/warden --path skills/warden-sweepManually: put the files in place
.devin/skills/warden-sweep/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add getsentry/warden --skill warden-sweep -a opencodeClaude.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 warden-sweep
How do I install warden-sweep in Claude Code?
Run npx skills add getsentry/warden --skill warden-sweep -a claude-code. It installs the skill into your Claude Code setup.
What command-line dependencies does warden-sweep require?
Your environment must have warden, gh, git, jq, and uv available in PATH. All commands execute from your project root.
How does the skill handle interrupted runs?
Results are logged inside .warden/sweeps/<run-id>/. The skill reads artifact files from the run directory and resumes execution from the first incomplete phase.
Source text
SKILL.md · Apache-2.0
---
name: warden-sweep
description: Full-repository code sweep. Scans every file with Warden, verifies findings through deep tracing, creates draft PRs for validated issues. Use when asked to "sweep the repo", "scan everything", "find all bugs", "full codebase review", "batch code analysis", or run Warden across the entire repository.
disable-model-invocation: true
---
# Warden Sweep
Run a full-repository Warden sweep: scan files, verify findings, create a tracking issue, open draft PRs for validated issues, and organize the final report.
**Requires**: `warden`, `gh`, `git`, `jq`, `uv`.
Run commands from the repository root. Use the host's skill-root path for bundled scripts and references.
Output goes to `.warden/sweeps/<run-id>/`.
## References
Load only the reference for the current phase:
| Need | Read |
|------|------|
| Script arguments, outputs, and side effects | `references/script-interfaces.md` |
| Phase 1 scan workflow | `references/scan-phase.md` |
| Phase 2 verification workflow | `references/verify-phase.md` |
| Phase 3 tracking issue workflow | `references/issue-phase.md` |
| Phase 4 patch and draft PR workflow | `references/patch-phase.md` |
| Phase 5 organize and final report workflow | `references/organize-phase.md` |
| Resume behavior and artifact layout | `references/resume-and-artifacts.md` |
| Verification task prompt template | `references/verify-prompt.md` |
| Patch task prompt template | `references/patch-prompt.md` |
## Workflow
Track progress across phases:
- [ ] Phase 1: Scan repository files with Warden.
- [ ] Phase 2: Verify findings before patching.
- [ ] Phase 3: Create a tracking issue.
- [ ] Phase 4: Patch verified findings and open draft PRs.
- [ ] Phase 5: Organize results and produce the final report.
## Phase Order
1. Read `references/script-interfaces.md` once before running scripts.
2. Run Phase 1 from `references/scan-phase.md`. Save `runId` and `sweepDir`.
3. Run Phase 2 from `references/verify-phase.md`. Verify every finding before patching.
4. Run Phase 3 from `references/issue-phase.md`. Continue if issue creation fails.
5. Run Phase 4 from `references/patch-phase.md`. Patch sequentially, one finding at a time.
6. Run Phase 5 from `references/organize-phase.md`.
7. For interrupted or partial runs, read `references/resume-and-artifacts.md` and continue from the first incomplete phase.
## Non-Negotiable Rules
- Verify findings before creating fixes.
- Use draft PRs for generated patches.
- Branch every patch from the repository default branch.
- Patch findings sequentially; do not run patch workers in parallel.
- Skip existing entries in sweep artifacts instead of duplicating work.
- Record failures in sweep data and continue to the next finding when possible.
- Clean up each worktree after patch success or failure.
## Final Response
After organizing, report:
```markdown
## Sweep Complete
| Metric | Count |
|--------|-------|
| Files scanned | {filesScanned} |
| Findings verified | {verified} |
| PRs created | {prsCreated} |
| Security findings | {securityFindings} |
Full report: `{summaryPath}`
```
© getsentry · Apache-2.0 · getsentry/warden