Harness Decay Audit — Security skill for Claude Code
Quarterly audit of rebar's harness components.
How to install Harness Decay Audit
Installs to ~/.claude/commands/spotcircuit-rebar-harness-decay-audit.md
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/spotcircuit/rebar/HEAD/.claude/commands/harness-decay-audit.md -o ~/.claude/commands/spotcircuit-rebar-harness-decay-audit.md Restart Claude Code, or start a new session, for it to be picked up.
What Harness Decay Audit does
allowed-tools: Read, Write, Edit, Glob, Grep, Bash description: Quarterly audit of rebar's harness components. Identifies commands/skills/agents that may have become dead weight as model capability improved, and proposes a kill-switch test for each. argument-hint: [scope] (optional — "commands", "agents", "skills", or omit for all)
Harness Decay Audit
**PRE-FLIGHT:** Confirm `pwd -P` equals `/mnt/c/Users/Big Daddy Pyatt/rebar`. This command reads `.claude/commands/`, `.claude/skills/
Alternatives in Security
- Deepsec — Deepsec is a security harness for finding vulnerabilities in your codebase powered by coding agents 7.8k ★
- T3mp3st — autonomous red teaming platform; multi-agent offensive-security meta-harness 5.7k ★
- Engage.Init — Initialize a new security engagement following the Kill Chain workflow 348 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Meta Retro
Monthly audit of the harness itself — prune dead weight, surface drift, update autonomy graduation. The retro
Risk Check
Define or audit hard risk limits, kill switch and pre-trade checks for a strategy or bot
Setup Dead Weight Audit
Audit Claude setup files for dead-weight instructions and config entries that would not change output or behav
Pause After Planning
Standing instruction: finish planning and verification (including plan-gate and plan-auditor), then stop so yo
Threat Report Killchain
Claude skill to convert CTI reports into cyber kill chain, Diamond Model views and create a TTP-to-ATT&CK/ATLA
Audit E2e
Audit end-to-end test coverage of critical Playwright paths. Identifies missing flows, flaky tests, slow suite
Related Agents
Loom Hermit
Loom Hermit - Simplification specialist that identifies and proposes removal of unnecessary complexity, bloat,
App Release Engineer
Get mobile builds to users predictably, with staged rollout and a kill switch that works. Invoke for mobile-te
PM Simplify Review
Read-only simplicity reviewer for Product Masters LMS diffs. Finds needless complexity, duplication, dead code