Redtropig

Redtropig/harness-anchor

Plugin Claude Code

Local dev marketplace for harness-anchor.

Redtropig/harness-anchor

Plugin Claude Code

Warn-only, zero-dependency runtime harness layer for Claude Code (companion to superpowers): persistent state, scope control (prompt + action side), Default-FAIL verification & coverage gates, entropy governance (golden-rules + drift detection), and first-class C/C++ engineering (CMake/Meson/Make/Bazel + clang-tidy +…

Redtropig/harness-anchor

Instructions file

Instructions for Redtropig/harness-anchor, covering harness-anchor — contributor & ai collaborator guidelines, if you are an ai agent editing this plugin, design invariants (do not break), shell hazards no tool in this repo catches and authoring a new skill (when explicitly asked).

Redtropig/harness-anchor

Agent

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…

Redtropig/harness-anchor

Agent

Use when C/C++ build fails — compile/link/configure error, missing header or package. Diagnoses root cause from build output. Read-only.

Redtropig/harness-anchor

Agent

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…

Redtropig/harness-anchor

Agent

Use when PROJECT-TOC.md needs rebuilding — after refactors, renames, or SessionStart tocstale. Runs index-builder.mjs. Writes only PROJECT-TOC.md.

Redtropig/harness-anchor

Agent

Use when user invokes /verify or calling agent needs fresh-context evaluation of done-ness. Runs build/tests/lint, reports evidence paths. Read-only.

Redtropig/harness-anchor

Command

Scaffold harness-anchor state files (AGENTS.md, featurelist.json, init.sh, progress.md, session-handoff.md, PROJECT-TOC.md) into the current project.

Redtropig/harness-anchor

Command

Initialize C/C++ project-specific harness files (.clang-format, .clang-tidy, sanitizer build, init.sh tuned per build system). Run AFTER /anchor.

Redtropig/harness-anchor

Command

On-demand code-drift / entropy scan (garbage collection) via a fresh-context drift-analyst subagent. Checks changed/active code against golden-rules.md + generic drift heuristics (dead code, duplication, doc-drift) and reports findings with an evidence path. Read-only — recommends, never auto-refactors. Not git gc.

Redtropig/harness-anchor

Command

(Re)build PROJECT-TOC.md — one-line index of every git-tracked source file, with git-commit freshness anchor.

Redtropig/harness-anchor

Command

Build a C/C++ project under runtime sanitizers (ASan+UBSan by default; TSan separately) and run its tests, reporting findings in fixed sections. Use for crashes, leaks, use-after-free, undefined behavior, or data races — or before merging C/C++ changes. Heavy build, so it is a command, never a hook.

Redtropig/harness-anchor

Command

Guided end-of-session ritual. Writes structured handoff (session-handoff.md), appends progress.md entry, and offers over-budget state archival + TOC refresh + git commit.

Redtropig/harness-anchor

Command

Show current project status — active feature, feature counts, git tree, TOC freshness, session handoff. Read-only overview. Distinct from /session-end (which writes).

Redtropig/harness-anchor

Command

Post-implementation coverage-gap analysis via a fresh-context coverage-analyst subagent. Derives test obligations from code + spec, flags paths/binaries outside the test runner's scope, and recommends a minimal, oracle-independent-first test set. Read-only — run before marking a feature 'pass'; complements /verify.

Redtropig/harness-anchor

Command

Run the full verification suite (build, type-check, tests, lint) via a fresh-context verification-runner subagent; reports evidence paths. Read-only by default; opt-in '--fix' runs a bounded auto-fix loop (max 2 cycles). Use before marking featurelist.json status as 'pass'.

Redtropig/harness-anchor

Hook

Runs when a session starts on startup, clear and compact, executing run-hook.cmd. From Redtropig/harness-anchor.

Redtropig/harness-anchor

Hook

Runs after a tool call finishes, executing run-hook.cmd. From Redtropig/harness-anchor.

Redtropig/harness-anchor

Hook

Runs before the context is compacted, executing run-hook.cmd. From Redtropig/harness-anchor.

Redtropig/harness-anchor

Hook

Runs when the agent finishes a response, executing run-hook.cmd. From Redtropig/harness-anchor.

Redtropig/harness-anchor

Hook

Runs when you submit a prompt, before the agent sees it, executing run-hook.cmd. From Redtropig/harness-anchor.

Redtropig/harness-anchor

Skill Claude CodeCodex

Use before claiming done/fixed/passing — or before asserting something is absent: not installed, not available, no such function, couldn't find it. Default-FAIL runs both ways — every claim needs an evidence path. A negative claim must carry its search scope and observation date; state calibrated uncertainty when…

Redtropig/harness-anchor

Skill Claude CodeCodex

Use when the same mistake or bad pattern recurs, when a code-review comment is really a convention worth enforcing, or when you catch AI-generated drift/slop and want it to never happen again. Encodes the lesson as a durable rule in golden-rules.md — the feedback-flywheel / harness-layer-learning ratchet — instead of…