backbay-labs/clawdstrike-tui-multi-agent-debug
.agents/skills/clawdstrike-tui-multi-agent-debug/SKILL.md
Use when a ClawdStrike TUI issue spans live reproduction, code tracing, implementation, official Codex docs verification, and review, and should be split across focused Codex sub-agents instead of handled serially.
$ install --global
skillsauthnpx skillsauth add backbay-labs/clawdstrike clawdstrike-tui-multi-agent-debugInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 3, 2026, 7:41 PM120.8s2 files scanned
SKILL.md
- name:
- clawdstrike-tui-multi-agent-debug
- description:
- Use when a ClawdStrike TUI issue spans live reproduction, code tracing, implementation, official Codex docs verification, and review, and should be split across focused Codex sub-agents instead of handled serially.
ClawdStrike TUI Multi-Agent Debug
Use this skill when one agent would end up mixing too many jobs: reproduction, repo mapping, docs validation, implementation, and review.
Role Split
Use the project roles in .codex/config.toml:
tui_explorerfor code-path mappingtui_dogfooderfor live PTY reproductionopenai_docs_researcherfor Codex config, AGENTS, skills, or multi-agent questionstui_workerfor the smallest fixtui_reviewerfor regression and verification review
Workflow
- Start with explorer and dogfooder in parallel when the failure mode is unclear.
- Add docs research only if the bug depends on Codex behavior, OpenAI docs, or configuration semantics.
- Do not let the worker start until reproduction and ownership are concrete.
- Hand the final diff to the reviewer before declaring the task complete.
- Keep each sub-agent narrow and opinionated; do not let reproduction agents edit code.
Good Fit
- a screen failure that may be runtime, wrapper, or layout related
- a Codex configuration issue involving
.codex/config.toml,AGENTS.md, or skills - a release-path bug that crosses
apps/terminal,hush-cli, and local runtime behavior
Bad Fit
- a tiny one-file change with obvious ownership
- pure docs edits with no live verification need
- a broad roadmap or brainstorming task
Related Skills
backbay-labs/hello-secure
testing
VerifiedTrustedCommunity
A simple skill demonstrating clawdstrike security
273SKILL.mdUpdated Apr 3, 2026
backbay-labs/examples/openclaw-plugin/skills/hello
tools
VerifiedTrustedCommunity
# Hello Skill A simple greeting skill that demonstrates secure agent operation. ## Description This skill allows the agent to greet users and perform basic file operations within the allowed workspace. ## Capabilities - Generate personalized greetings - Read files from the workspace - Write greeting logs to the output directory ## Usage Ask the agent: - "Say hello to Alice" - "Read the welcome message from data/welcome.txt" - "Log a greeting for Bob" ## Examples ### Basic Greeting **Us
273SKILL.mdUpdated Apr 3, 2026
backbay-labs/examples/bb-edr/skills/edr-triage
testing
VerifiedTrustedCommunity
# bb-edr: Triage Skill Use this skill to turn clawdstrike audit logs into an incident report and a minimal response plan. ## Inputs - `.hush/audit.jsonl` (JSONL) — clawdstrike audit events (allowed/denied, guard, reason). - `policy.yaml` — the active security policy. ## Task 1. Read and summarize the last ~50 audit events. 2. Focus on **denied** events first: - Group by `guard` (e.g., `forbidden_path`, `egress`, `patch_integrity`) - Identify likely intent (misconfiguration vs. suspici
273SKILL.mdUpdated Apr 3, 2026
backbay-labs/cursor-plugin/skills/threat-hunt
tools
VerifiedTrustedCommunity
Threat hunting and security event investigation
273SKILL.mdUpdated Apr 3, 2026