Install
$ agentstack add skill-franklywatson-claude-rig-debug-plus ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
debug+ — Systematic Debugging with Scout Context
Wraps superpowers:systematic-debugging. Requires superpowers to be installed.
No phase prerequisite — invoke from any skill chain phase when you encounter a bug, test failure, or unexpected behavior.
Before You Begin
This skill adds scout-mandated context harvesting on top of the base debugging skill:
- Scout context — always map the affected code area via the scout agent before debugging
- Environment awareness — detects test infrastructure, dependencies, and recent changes
- Constitutional awareness — loads active enforcement rules from session context
Procedure
Phase A: Harvest Context
- Reproduce the issue — run the failing command or test and capture the exact output.
- Invoke the scout agent to map the affected area:
`` Agent(subagent_type="scout", prompt="Map the codebase around [affected files/modules]. Focus on: related functions, callers, test files, and recent changes.") ``
- Identify:
- The exact failure symptom (error message, wrong output, crash)
- The code path that produces the symptom
- Recent changes that may have introduced the issue
- Related test coverage
- Active enforcement rules from session context (see session-start output)
Phase B: Investigate (delegate to superpowers:systematic-debugging)
- Invoke
superpowers:systematic-debuggingwith the gathered context.
- Follow the systematic debugging process:
- State the hypothesis before investigating
- Verify the hypothesis with evidence (command output, file reads)
- If the hypothesis is wrong, state why and form a new one
- Show the evidence at each step
Phase C: Report Findings
- Produce a finding summary:
``` ## Investigation Report
### Symptom [Exact failure description]
### Root Cause [What caused the issue]
### Evidence
- [Evidence 1: command output or file content]
- [Evidence 2: ...]
### Fix [Specific change needed to resolve the issue] ```
- If the fix is straightforward, implement it and run the relevant tests.
If the fix requires a larger change, return to the current phase with the finding.
Skill Chain
/debug+ has no phase prerequisite — invoke it from any phase when you need to debug a bug or investigate unexpected behavior. After resolving the investigation, return to your current phase.
Completion
Report one of these states when the skill finishes:
- DONE — Root cause identified and fix applied with passing tests.
- DONEWITHCONCERNS — Root cause identified but fix has side effects or needs review.
- BLOCKED — Cannot reproduce the issue or insufficient context to diagnose.
- NEEDS_CONTEXT — Need user input to reproduce the issue or understand expected behavior.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: franklywatson
- Source: franklywatson/claude-rig
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.