A warn-only runtime layer for Claude Code agents. Keeps feature state, scope and handoffs on disk so they survive compaction, and requires an evidence path before a done claim. Never blocks a tool call. Companion to superpowers; bash + git, no MCP.
Agent
Part of harness-anchor
Use when /test-plan runs or the calling agent needs a fresh-context coverage-gap analysis before a feature is called done. Derives test obligations from code + spec (post-implementation, gray-box), finds gaps — including paths and built binaries that sit OUTSIDE what the test runner executes — and recommends a…
Agent
Part of harness-anchor
Use when C/C++ build fails — compile/link/configure error, missing header or package. Diagnoses root cause from build output. Read-only.
Agent
Part of harness-anchor
Use when /gc runs or the calling agent needs a fresh-context scan for code drift, entropy, or AI slop before wrapping up. Checks changed/active code against the project's golden-rules.md plus generic drift heuristics (duplicated helpers, inconsistent error handling, copy-paste blocks, oversized files, TODO pileup…
Agent
Part of harness-anchor
Use when PROJECT-TOC.md needs rebuilding — after refactors, renames, or SessionStart tocstale. Runs index-builder.mjs. Writes only PROJECT-TOC.md.
Agent
Part of harness-anchor
Use when user invokes /verify or calling agent needs fresh-context evaluation of done-ness. Runs build/tests/lint, reports evidence paths. Read-only.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: