claude

traces

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.

3 on GitHubv1.4.1updated 5 months agodiagnostics
/

Plugin traces 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.

What it installs

Skills (7)

  • failure-attribute

    Use when a regression appears — a test that passed last week now fails, behavior changed unexpectedly, or you need to know which change introduced the problem before choosing a rollback target. Walks recent manifest entries in reverse-chronological order, re-runs each entry's declared verifier_oblig

  • reasoning-tilt

    Use when you want to detect whether a session's command and output text is leaning toward forward-looking framing ("next", "let me try", "plan to") vs. history-following framing ("blocked", "failed", "can't"). Scores a JSONL trace file with a forward/history lexical ratio and flags sessions that hav

  • trace-clarification

    Use when the user wants to know how often clarification arrives mid-trajectory and how much pre-clarification work gets wasted. Computes the pre-clarification action ratio per session from JSONL traces — the fraction of bash and file events that occurred before the first follow-up user turn.

  • trace-compile

    Compile raw JSONL traces from `.claude/traces/` into structured summary and error views.

  • trace-evolve

    Analyze execution traces to cluster failure patterns and propose harness improvements (rules, hooks, skills).

  • trace-review

    Analyze recent execution traces to find recurring patterns, failures, and optimization opportunities.

  • trace-stats

    Use when the user wants a fast numeric summary of recent sessions — command counts, error rates, files modified, average tokens per turn — without the cost of full pattern analysis. Runs against `.claude/traces/*.jsonl` and returns a one-screen table.

Hooks (6)

  • UserPromptSubmit

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/collect-user-turn.sh

  • PostToolUse

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/collect-bash-trace.sh

  • PostToolUse

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/collect-file-trace.sh

  • PostToolUseFailure

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/collect-failure-trace.sh

  • StopFailure

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/log-stop-failure.sh

  • SessionEnd

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/session-summary.sh

View source on GitHub

More from ArtMin96/forge-studio

All 21 plugins →

evaluator

claude

Evaluator-optimizer pattern: adversarial review, verification gates (TaskCompleted), static analysis, postmortems, reference-fidelity check, self-evolution proposal assessment.

14 skills · 1 agent · hooks

3

workflow

claude

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.

11 skills · hooks

3

agents

claude

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

3

diagnostics

claude

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

3

forge-meta

claude

Self-evolution boundary: change-manifest writer, evolution-history ledger, session-digest, auto-tune-skill outer loop, controllability invariant (POLICY.md).

8 skills · hooks

3

context-engine

claude

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

3

Similar plugins

telemetry

claude

Plugin analytics: hooks $.telemetry's two events, so a plugin logs an event or marks a feature's use as a first-party row, sent in batches with the session's own credential.

anthropics/claude-code 155,476

ruflo-observability

claude

Structured logging, distributed tracing, and metrics — correlate agent swarm activity with application telemetry

2 skills · 1 command · 1 agent

ruvnet/ruflo 81,589

gitnexus

claudecodex

Code intelligence powered by a knowledge graph. Provides execution flow tracing, blast radius analysis, and augmented search across your codebase.

12 skills · 1 MCP server · hooks

abhigyanpatwari/GitNexus 48,482

azure

claude

Transform Claude into an Azure expert. This plugin integrates the Azure MCP server and specialized Azure skills to move beyond generic advice. It enables Claude to perform real-world tasks: listing resources, validating deployments, diagnosing infrastructure issues, and optimizing costs across 50+ Azure services.

44 skills · 1 MCP server

anthropics/claude-plugins-official 47,076

ifixai

claudecodex

Independent auditing for AI agents, open source. Claude discovers your setup, confirms the cost, and audits your agent against the one question other tools skip: is it doing the job it's supposed to do, given your business rules and org structure? Test any model (Anthropic, OpenAI, Gemini, Azure, Bedrock, …) graded by self, one independent judge, or a cross-vendor panel; each provider is billed to its own account via a key in your settings, never the command line. Results render as an interactive artifact (with a static-report fallback).

1 skill · hooks

ifixai-ai/iFixAi 45,158

Maintain traces?

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.

claude & codex plugins21 plugins