Counterfactual A/B + layered-ablation harness for Claude Code setup. Measures whether your /.claude/ stack (skills, lessons, axioms, memory) plus in-repo discipline (docs/runbooks, decisions, findings) actually helps on real tasks. Binary A/B (setup-ON vs setup-OFF) and layered ablation (strip one layer at a time, ran.
★not rated 1 18d agoA
tokens not measured
originalMIT
Wire up CI validation and automatic release-cutting for a Claude Code plugin or marketplace repo (one with a .claude-plugin/marketplace.json and plugins/). Adds two GitHub Actions — a structure validator on every PR/push, and a release-on-version-bump job that cuts a GitHub Release whenever VERSION changes — plus the.
★not rated 1 18d agoA
tokens not measured
originalMIT
Measure, trim, and report the token cost of a runaway Claude Code skills/agents catalog (injected every turn + into every subagent) — verified per-project skillOverrides + global disable-model-invocation levers, an interactive HTML recap, and the durable root-cause fix (curate episodic lessons out of the always-on…
★not rated 1 18d agoA
tokens not measured
originalMIT
Detect stale normative guidance in project docs/ after the user adds a new "don't X / avoid Y" rule to /.claude/lessons.md, /.claude/axioms.md, or a per-project feedback.md entry. Event-driven PostToolUse hook + weekly cron audit. Lists file:line candidate stale claims — never auto-edits. Conservative guardrails: e.
★not rated 1 18d agoA
tokens not measured
originalMIT
A check reported clean without examining the case it exists for — "green" meant "nothing ran". Use when about to trust a gate, test or CI step you have never watched fail; when a guard is green but the bug it guards shipped anyway; when a check passes on a shallow clone, a disabled object, a malformed input or an…
★not rated 1 18d agoA
tokens not measured
originalMIT
Audit and clean up Claude Code's persistent memory system — MEMORY.md, memory topic files, lessons, axioms, phase templates, ADRs, and the project docs/ taxonomy.
★not rated 1 18d agoA
tokens not measured
originalMIT
Pre-PR checklist and repo cleanup for data-science / analytics projects. Catches mistakes that cost hours later: data files committed to git (.csv/.db/.parquet), hardcoded /Users/ paths, tracked runtime artifacts, branch-ownership confusion, internal docs drifting from deliverables, and client data in public repos.…
★not rated 1 18d agoA
tokens not measured
originalMIT
Scan a portfolio of authored Claude Code skills and produce, per target repo, a precise list of which skills to ADD, which to UPDATE (with drift direction), and which to CROSS-LINK rather than copy. Uses per-repo function-level inclusion bars, portfolio deduplication (never recommend a skill already homed elsewhere)…
★not rated 1 18d agoA
tokens not measured
originalMIT
Quantitatively measure how effective a project's automated test suite is at catching real bugs, by replaying historical incidents at pre-fix commits and classifying CI failure history.
★not rated 1 18d agoA
tokens not measured
originalMIT
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: