claude

agents

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.

3 on GitHubv1.3.0updated 5 months agomulti-agent
/

Plugin agents 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 (5)

  • contract

    Use whenever a generator agent or implementation step is about to begin work from a plan file — re-read the sprint contract verbatim and confirm the success criteria before writing any code. Prevents context decay by forcing a fresh Read of the criteria from disk rather than trusting earlier-in-sess

  • dispatch

    Use when the user describes a multi-step feature or refactor and you need to decide whether to handle it solo, dispatch a parallel `/fan-out`, or run a `/worktree-team` planner→generator→reviewer pipeline. Outputs a routing recommendation with the reasoning behind it.

  • fan-out

    Use whenever the user asks to apply the same operation to many independent files or components — bulk migration, batch refactor across controllers, parallel exploration of unrelated subsystems. Dispatches one subagent per file with a shared prompt template, then collects the results.

  • lean-agents

    Use when subagent dispatches feel expensive — token budget tight, per-turn cost ballooning in multi-agent workflows, or when planning a `/fan-out` over many files. Recommends a 4-layer isolation profile (CLAUDE_CODE_SIMPLE, narrowed `allowed-tools`, capped `maxTurns`, picked `model`) that drops suba

  • worktree-team

    Use when two or more streams of work must not interleave edits — concurrent feature branches, long-running research alongside implementation, or any time `/fan-out` would race because items share mutable state. Bootstraps N (max 5) parallel agents each in an isolated git worktree with a role-scoped

Subagents (4)

  • generator

    Implementation agent that writes code from an approved plan. Use proactively after a planner has produced a plan and code needs to be written, or when executing a Pipeline (Planner → Generator → Reviewer). Full read-write access; follows existing patterns and conventions.

  • planner

    Exploration + plan-authoring agent. Analyzes the codebase, proposes an implementation approach, and writes the resulting plan to `.claude/plans/s<N>-<slug>.md` in canonical format. Write/Edit scope is restricted to `.claude/plans/` by convention — source files are off-limits during planning.

  • researcher

    Deep research and information-gathering specialist. Use proactively whenever the user asks to research, investigate, understand, explore, trace, or find something in the codebase ("where is X", "how does X work", "what calls X", "map the dependencies of X"), and before planning a non-trivial change

  • reviewer

    Read-only critic agent that reviews implementation for bugs, edge cases, and convention violations. Use proactively after any generator-produced change, before merging a branch, or when high-risk code needs a skeptical second pass. Cannot modify code — separation ensures honest evaluation.

Hooks (4)

  • SubagentStart

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/contract-reread.sh

  • SubagentStop

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/contract-check.sh

  • SubagentStop

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/output-schema-check.sh

  • PreToolUse

    bash ${CLAUDE_PLUGIN_ROOT}/hooks/directory-ownership.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

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

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

8 skills · hooks

3

traces

claude

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

3

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

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

context7

claudecodex

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

upstash/context7 64,709

5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.

5 skills · 16 commands · 4 agents · hooks

Imbad0202/academic-research-skills 56,698

Automates browser interactions for web testing, form filling, screenshots, and data extraction

12 skills

vercel-labs/agent-browser 50,373

Maintain agents?

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