Agent Claude Code
Explore a subsystem or module and produce Mermaid architecture diagrams documenting data flows, component relationships, and system context.
not rated 66 3mo ago A 26 tokens
original MIT
66Stars on the repository
116Mods indexed here, across every type
3mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown
Agent Claude Code
Proactively audit the assumption registry for stale, unverified, or newly-broken assumptions. Use on a schedule (weekly) or when starting work that depends on external systems. Unlike dependency-verifier (reactive, investigates on demand), this agent walks the full registry and flags what needs attention.
not rated 66 3mo ago A 65 tokens
original MIT
Agent Claude Code
Maintain awareness of all active workstreams, prevent conflicts between parallel tasks, and ensure unblocked work continues moving. Use for status checks, dependency analysis, task reordering, and detecting conflicts between parallel workstreams.
not rated 66 3mo ago A 47 tokens
original MIT
Agent Claude Code
Track aggregate token spend and API costs across all agent operations. Enforce budget constraints, detect cost anomalies, and recommend budget reallocation. Use for daily cost rollups, budget enforcement, and spend optimization.
not rated 66 3mo ago A 46 tokens
original MIT
Agent Claude Code
Verify that external dependencies, APIs, specs, and tools actually behave as documented. Use when you need to validate assumptions about external systems, check if a spec is actually implemented, or investigate ecosystem adoption of a feature. This agent tests against real-world implementations, not just documentation.
not rated 66 3mo ago A 59 tokens
original MIT
Agent Claude Code
Adversarial reviewer that systematically attacks specs, implementations, and plans to find logical gaps, missed edge cases, implicit assumptions, and over/under-engineering. Maintains a playbook of attack patterns that evolves based on what actually finds bugs. Use on any artifact you want stress-tested before…
not rated 66 3mo ago A 66 tokens
original MIT
Agent Claude Code
Use proactively to verify claims in documentation against sources of truth (codebase, web data, or research). Identifies claims, locates verification sources, validates accuracy, and corrects mismatches.
not rated 66 3mo ago A 44 tokens
original MIT
hook-health
08Agent Claude Code
Monitor and diagnose hook failures, silent data corruption, and schema mismatches in the .claude/hooks/ infrastructure. Use when hooks timeout, produce wrong data, or fail silently. This agent diagnoses but cannot directly fix hooks due to write-protection — it produces template patches for human installation.
not rated 66 3mo ago A 61 tokens
original MIT
Agent Claude Code
Thoughtbox Hub ARCHITECT agent. Joins workspaces, analyzes structure, designs solutions, creates proposals. Use for design and architecture work in multi-agent collaboration.
not rated 66 3mo ago A 37 tokens
original MIT
hub-debugger
10Agent Claude Code
Thoughtbox Hub DEBUGGER agent. Joins workspaces, claims bug problems, performs root cause analysis using five-whys, reviews proposals for correctness. Use for debugging and bug investigation in multi-agent collaboration.
not rated 66 3mo ago A 45 tokens
original MIT
hub-manager
11Agent Claude Code
Thoughtbox Hub MANAGER agent. Creates workspaces, decomposes problems, coordinates contributors. Use when orchestrating multi-agent collaboration on the hub.
not rated 66 3mo ago A 32 tokens
original MIT
meta-agent
12Agent Claude Code
Generates a new, complete Claude Code sub-agent configuration file from a user's description. Use this to create new agents. Use this Proactively when the user asks you to create a new sub agent.
not rated 66 3mo ago A 43 tokens
original MIT
Agent Claude Code
Watch evaluation metrics over time for trends and regressions. Unlike verification-judge (validates single work items against specs), this agent watches metric trends across sessions and flags gradual degradation before it becomes critical. Use after session-end metrics collection or as a daily rollup.
not rated 66 3mo ago A 58 tokens
original MIT
Agent Claude Code
Evaluate research directions before committing effort. Use when deciding whether to pursue a technical investigation, feature direction, tool evaluation, or any significant research investment. This agent prevents wasted effort by identifying the highest-information, lowest-cost path through a problem space.
not rated 66 3mo ago A 52 tokens
original MIT
Agent Claude Code
Specialized adversarial agent for finding code paths that fail without producing visible errors. Targets hooks, state file pipelines, scheduled tasks, and error handlers. Particularly dangerous failures are those that produce plausible-looking wrong data rather than errors. Shares the adversarial playbook with…
not rated 66 3mo ago B 64 tokens
original MIT
Agent Claude Code
Use proactively for exploring creative, non-obvious applications of Supabase Auth, Row-Level Security, and GraphQL for Thoughtbox, where "users" are AI agents rather than humans. Specialist for generating surprising identity-dimension design proposals grounded in metaphors of theatrical masks, legal personhood, and…
not rated 66 3mo ago A 99 tokens
original MIT
Agent Claude Code
Use proactively for exploring creative, non-obvious applications of Supabase Edge Functions, AI (embeddings and LLM integrations), and Queue-triggered asynchronous inference for Thoughtbox. Operates under a committed metaphor of municipal public works, emergency services dispatch, and the reflex arc. Invoke when the…
not rated 66 3mo ago A 93 tokens
original MIT
Agent Claude Code
Specialist research agent for discovering creative, non-obvious applications of the Supabase SUBSTRATE dimension (Postgres Database, Storage object store, pgvector) to Thoughtbox's reasoning-persistence surfaces. Use proactively when exploring how substrate-layer primitives could become new "organs" for Thoughtbox…
not rated 66 3mo ago A 117 tokens
original MIT
Agent Claude Code
Use proactively when exploring creative, non-obvious applications of Supabase's temporal features (Realtime, Queues, Cron) for Thoughtbox. Specialist for generating surprising use cases through the lens of circadian biology and musical meter. Invoke when brainstorming how Thoughtbox could grow new "organs"…
not rated 66 3mo ago A 88 tokens
original MIT
Agent Claude Code
Persistent background teammate that monitors Thoughtbox sessions for evolution candidates, contradiction detection, and session digests. Runs alongside the lead agent during Thoughtbox-heavy work sessions. Use as a teammate in an Agent Team, not as a standalone sub-agent.
not rated 66 3mo ago A 54 tokens
original MIT
triage-fix
21Agent Claude Code
Diagnose and repair technical failures in the codebase, build system, and integrations. Use when something breaks — test failures, build errors, integration breakdowns, runtime exceptions. This agent implements fixes autonomously within scope boundaries.
not rated 66 3mo ago A 50 tokens
original MIT
Agent Claude Code
Independently validate completed work against specifications and acceptance criteria. Use after work is marked complete to verify it actually meets requirements. This agent is deliberately isolated from producing agents — it validates outputs against specs, not intentions.
not rated 66 3mo ago A 47 tokens
original MIT
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: