plastic
01Plugin Claude Code
Marketplace for Plastic: intent-driven state management.
10 2d ago A
tokens not measured
original MIT
plastic
02Plugin Claude Code
Intent-driven state management for AI coding sessions. Neuroplasticity for your codebase.
10 2d ago A
tokens not measured
original MIT
plastic
03Settings file Claude Code
Agent settings declaring 7 allowed tools.
10 2d ago A
tokens not measured
original MIT
enola
04MCP server Claude CodeCodexCursor +2
MCP server "enola" as configured in zalom/plastic. Launched with enola. Needs 1 environment variable to run.
10 2d ago A
tokens not measured
original MIT
Instructions file CodexOpenCode
Instructions for zalom/plastic, covering plastic, stack, defaults, searching plastic with qmd and working on plastic.
10 2d ago A 2,141 tokens
original MIT
Instructions file
Instructions for zalom/plastic: Project conventions and contributor rules live in AGENTS.md. Follow them.
10 2d ago A 22 tokens
original MIT
Agent
The real advisor: expensive, consultation-only, dispatched deliberately by the user or main session for the hardest reasoning, never by the auto pipeline. State TIER: S, M, or L in the brief, plus an EFFORT line. S: one bounded decision, verdict plus biggest risk. M: plan or plan-review, decision plus stepped plan…
10 2d ago A 124 tokens
original MIT
Agent
Use for the Why-stage exploration of an active intent in auto mode: enrich the intent's Context and record its Decisions before the spec is written.
10 2d ago A 36 tokens
original MIT
Agent
Use as the auto-mode orchestrator: it spins up the team, sequences the specialists, owns every gate, and runs the final review.
10 2d ago A 34 tokens
original MIT
Agent
Use for the Exec stage in auto mode: implement the actions, check off the checklist, and drive the test suite green.
10 2d ago A 31 tokens
original MIT
Agent
The imitation advisor: an ordinary model carrying the frontier reasoning discipline below, so it reasons like the real advisor at a fraction of the cost. Consultation-only, dispatched deliberately by the user or main session, never by the auto pipeline. State TIER: S, M, or L in the brief, plus an EFFORT line. S: one…
10 2d ago A 153 tokens
original MIT
Agent
Use to research a parked future intent autonomously via web search and codebase analysis, writing the findings into the intent.
10 2d ago A 34 tokens
original MIT
Agent
Use when completing or reviewing intents, reorganizing INDEX.md, or maintaining the intent store.
10 2d ago A 25 tokens
original MIT
Agent
Use for the What-stage context deposit when an intent is activated: run QMD discovery and write findings to resources/, never the intent file itself.
10 2d ago A 37 tokens
original MIT
Agent
Use for the How stage in auto mode: turn spec.md into plan.md, self-contained action files, and checklist.md.
10 2d ago A 30 tokens
original MIT
Agent
Use at the Why-to-How boundary in auto mode: consolidate the enriched Why into spec.md from the spec template.
10 2d ago A 30 tokens
original MIT
SessionStart
17Hook
Runs when a session starts, running an inline shell check (2 commands). From zalom/plastic.
10 2d ago A
tokens not measured
original MIT
PreCompact
18Hook
Runs before the context is compacted, running an inline shell check. From zalom/plastic.
10 2d ago A
tokens not measured
original MIT
PreToolUse
19Hook
Runs before the agent uses a tool for Write, Edit, NotebookEdit, mcp__serena__replace_content, mcp__serena__replace_symbol_body, mcp__serena__insert_after_symbol, mcp__serena__insert_before_symbol, mcp__serena__safe_delete_symbol, mcp__serena__rename_symbol and Bash tool calls, running an inline shell check (2…
10 2d ago A
tokens not measured
original MIT
PostToolUse
20Hook
Runs after a tool call finishes for Write and Edit tool calls, running an inline shell check. From zalom/plastic.
10 2d ago A
tokens not measured
original MIT
Hook
Runs when you submit a prompt, before the agent sees it, running an inline shell check (4 commands). From zalom/plastic.
10 2d ago A
tokens not measured
copy · 64% MIT
Skill Claude CodeCodex
Consult the advisor for expensive reasoning: one-way doors, plans, adversarial review of a plan or conclusion before an irreversible step, a deadlock after two failed attempts, or ranking several plausible options. Use when the user asks for a second opinion, a hard design decision, an architecture review, help…
10 2d ago A 104 tokens
original MIT
plastic-auto
23Skill Claude CodeCodex
Autonomous intent delivery - agent takes over How and Exec. Use when user says "auto", "take it from here", "deliver this", or when brainstorming-grill-me concludes and user confirms autonomous execution. Requires an active intent in INDEX.md.
10 2d ago A 53 tokens
original MIT
Skill Claude CodeCodex
Use when the user says "continue", "resume", or "pick up where we left off", starts a new session and wants to keep going, asks "what should I work on", or asks a where-was-I question that never says "continue" (for example "where was I"). This is the front door for resuming work: it dispatches to…
10 2d ago A 123 tokens
original MIT