SessionEnd
25Hook
Runs when a session ends, running node. From mareurs/claude-plugins.
2 2d ago A
tokens not measured
PostToolUse
26Hook
Runs after a tool call finishes, running node. From mareurs/claude-plugins.
2 2d ago A
tokens not measured
Hook
Runs when you submit a prompt, before the agent sees it, running node. From mareurs/claude-plugins.
2 2d ago A
tokens not measured
Skill Claude CodeCodex
System boundaries, module design, interface decisions.
2 2d ago A 14 tokens
Skill Claude CodeCodex
Auditing codescout tool-call usage — inefficient tool patterns, recurring frictions, hookify candidates.
2 2d ago A 24 tokens
Skill Claude CodeCodex
ML data hygiene, evaluation integrity, train/test leakage (lens required: classic or llm).
2 2d ago A 29 tokens
Skill Claude CodeCodex
Bug resists surface fixes, flaky tests, failure doesn't match symptom.
2 2d ago A 18 tokens
Skill Claude CodeCodex
Technical writing, documentation architecture.
2 2d ago A 11 tokens
Skill Claude CodeCodex
Training loops, inference parity, ML pipeline issues.
2 2d ago A 14 tokens
Skill Claude CodeCodex
Profiling, latency, throughput, optimization.
2 2d ago A 14 tokens
Skill Claude CodeCodex
Work planning, task sequencing, breaking down large efforts.
2 2d ago A 14 tokens
prompt-hamsa
36Skill Claude CodeCodex
Improving a prompt — critique, drafting from scratch, diagnosing model misbehavior, or coaching toward eval-driven iteration.
2 2d ago A 27 tokens
Skill Claude CodeCodex
Structural code transformation, cleaning up tangled code.
2 2d ago A 13 tokens
Skill Claude CodeCodex
Security review, threat modeling, vulnerability analysis.
2 2d ago A 13 tokens
Skill Claude CodeCodex
Designing test suites, coverage gaps, flaky tests, asserting correctness.
2 2d ago A 19 tokens
Plugin Claude Code
Rich, color-coded terminal status line showing model, context %, rate limits (incl. per-model weekly), git info, and more.
2 2d ago A
tokens not measured
Command
Copies the claude-statusline script to /.claude/statusline.sh and configures settings.json.
2 2d ago B 0 tokens
Command
Removes the claude-statusline integration: prunes the statusLine entry from /.claude/settings.json and optionally deletes /.claude/statusline.sh.
2 2d ago B 0 tokens
Plugin Claude Code
Companion plugin for codescout MCP server. Injects the project system-prompt into subagents, warns on Read/Grep/Glob misuse, auto-reindexes stale projects, and surfaces drift warnings.
2 2d ago A
tokens not measured
dashboard
44Command
Launch the codescout dashboard web UI for the current project.
2 2d ago C 11 tokens
Skill Claude CodeCodex
Use when you explicitly want a READ-ONLY exploration of a DIFFERENT repo than the current one, returned as a structured findings report. Dispatches a subagent at the target repo; the explore-inject hook auto-bootstraps that project's CLAUDE.md + codescout memories. Routine cross-repo dispatches do NOT need this — the…
2 2d ago A 81 tokens
Skill Claude CodeCodex
Use before subagent dispatch, before editing code that changes a struct, function signature, or API contract, or after a tool response contradicts the plan. Appends friction (F-N) and wins (W-N) to the project's session-log tracker.
2 2d ago A 56 tokens
Skill Claude CodeCodex
Use when the user runs /research-subagent or asks for deep research, a full report, or research where the main context should not absorb raw search results — including mapping a broad subject across multiple angles (fan-out). Spawns one or more general-purpose subagents that call the researcher MCP and return only…
2 2d ago A 78 tokens
research-web
48Skill Claude CodeCodex
Use when the user runs /research-web or asks for web research on a topic, person, company, library, market, or jobs and wants results inline in the current conversation. Calls the researcher MCP directly; results land in main context. Prefer /research-subagent if context is precious or the user asked for a deep/report…
2 2d ago A 71 tokens