evaluator
claudeEvaluator-optimizer pattern: adversarial review, verification gates (TaskCompleted), static analysis, postmortems, reference-fidelity check, self-evolution proposal assessment.
14 skills · 1 agent · hooks
Hook-driven agentic workflow orchestrator. Automatic routing (shell or LLM-hybrid), sprint-contract enforcement, TDD loop, session bootstrap, handoff nudges. Self-evolution SEPL loop (propose/assess/commit/rollback) over versioned resources. Composes agents/evaluator/context-engine/memory rather than duplicating them.
Plugin workflow from marketplace forge-studio in ArtMin96/forge-studio. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
commit-proposalUse to apply an assessed self-evolution proposal — snapshots the prior resource version under `.claude/lineage/versions/`, writes the new content, and appends a commit entry to the ledger. Refuses to run unless the most recent `assess` verdict is `pass` and the user has explicitly approved.
convergence-checkInternal helper — parses a plan file's `## Convergence` section and evaluates its `criterion` shell command against current state. Returns a structured report with `met`, `evidence`, and `gap` fields. Called by /verify and /status; not for direct user invocation.
evolveRun a self-evolution cycle. Consumes a proposal source (trace-evolve output, router-tune output, manual proposal), routes through /assess-proposal, asks for user approval, hands off to /commit-proposal. Never mutates harness files without consent.
living-specInitialize .claude/spec.md from the latest plan's ## Contract. after-subagent.sh then appends delta blocks as each agent completes. Pairs with /contract (static criteria) + /feature-list (testable JSON) to form the plan→execute→verify loop.
orchestrateManually invoke the agentic workflow for the current task. Reads the active plan and dispatches the right pattern (single-agent, pipeline, fan-out, TDD loop).
reflectUse after a completed sprint or `/tdd-loop` finishes — reads the plan's contract, test output, and git diff, emits a three-line insight (what worked / what surprised / what to watch), and routes the lesson to `/remember` if it deserves persistence. Optional but recommended phase to convert successfu
rollbackUse to reverse a prior self-evolution commit — restores a snapshot from `.claude/lineage/versions/<slug>/<version>` and appends a rollback entry to the ledger. The rollback itself is logged so history stays append-only and auditable.
router-tuneAnalyze router classification history, cluster miss-fires, emit a proposal artifact tweaking route-prompt.sh thresholds or regex rules. Feeds /evolve.
statusOn-demand snapshot of where the session stands — active plan, last progress-log entry, recent traces, context pressure. Composes existing plugins; no new persistence.
tdd-loopUse when building a new feature or reproducing a bug test-first — drives a Red-Green-Refactor loop with three real-command completion gates (failing test exists → test passes → no regressions). Each phase runs in an isolated subagent so context from one phase can't leak into the next and produce pre
zoom-outUse when the user is unfamiliar with a section of code, asks "what does this fit into", "where does this get called from", or wants a higher-level map before diving into a specific function — returns a one-screen map of relevant modules, callers, and the layer above the current file.
W=${CLAUDE_PLUGIN_ROOT}/diagnostics-lib/time-hook.sh; H=${CLAUDE_PLUGIN_ROOT}/hooks/session-bootstrap.sh; if [ -x "$W" ]; then bash "$W" workflow SessionStart bash "$H"; else bash "$H"; fi
bash ${CLAUDE_PLUGIN_ROOT}/hooks/route-prompt.sh
bash ${CLAUDE_PLUGIN_ROOT}/hooks/after-subagent.sh
bash ${CLAUDE_PLUGIN_ROOT}/hooks/plan-format-check.sh
bash ${CLAUDE_PLUGIN_ROOT}/hooks/turn-gate.sh
bash ${CLAUDE_PLUGIN_ROOT}/hooks/pre-compact-handoff.sh
Evaluator-optimizer pattern: adversarial review, verification gates (TaskCompleted), static analysis, postmortems, reference-fidelity check, self-evolution proposal assessment.
14 skills · 1 agent · hooks
Multi-agent decomposition: planner/generator/reviewer pipeline triad with tool-isolated capability boundaries, plus a read-only researcher for pre-planning investigation. Includes /worktree-team for physical worktree isolation, directory-ownership enforcement (opt-in), and output-schema checks on generator exit.
5 skills · 4 agents · hooks
Codebase health scanning: documentation drift, registration gaps, convention violations, stale memory, HARNESS_SPEC invariant compliance. /validate-marketplace performs pre-commit mechanical correctness checks (distinct from /entropy-scan). /startup-profile reports SessionStart hook latency. /policies-list prints the cross-plugin enforcement registry (FS01–FS42).
8 skills · hooks
Self-evolution boundary: change-manifest writer, evolution-history ledger, session-digest, auto-tune-skill outer loop, controllability invariant (POLICY.md).
8 skills · hooks
Execution trace collection, analysis, and harness evolution. Stores structured JSONL traces for pattern detection and failure-driven improvement. Feeds /evolve as a proposal source, plus per-session clarification-waste analysis.
7 skills · hooks
Context management: progressive pressure tracking, drift detection, edit safety, large-file warnings, plan mode hooks, MCP monitoring, prompt budget awareness, failure-escalation with safe-mode flag.
6 skills · hooks
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Persistent memory for Claude Code: the next session starts where the last one left off.
29 skills · 1 MCP server · hooks
Cross-session memory and token savings for coding agents.
6 skills · 1 agent · 1 MCP server · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Automates browser interactions for web testing, form filling, screenshots, and data extraction
12 skills
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.