CALM
01Plugin Claude Code
CALM (Coding Agent Liveness Map) — code-intelligence MCP server for coding agents.
Plugin Claude Code
CALM (Coding Agent Liveness Map) — code-intelligence MCP server for coding agents.
Hook Claude Code
Runs when a session starts, executing session-start-agents-md.sh and session-start-build-calm.sh via bash (2 commands). From Eilodon/CALM.
Hook Claude Code
Runs before the agent uses a tool for Read, Edit, Write, Grep, Bash, mcp__calm__edit_context, mcp__calm__diff_impact, mcp__calm__edit_lines, mcp__calm__edit_symbol, mcp__calm__search, mcp__calm__source, mcp__calm__locate, mcp__calm__file_overview, mcp__calm__understand and mcp__calm__session_context tool calls…
Hook Claude Code
Runs after a tool call finishes for Bash and Grep tool calls, executing calm-nudge.sh and posttooluse-discovery-dump.sh via bash (2 commands). From Eilodon/CALM.
Settings file Claude Code
Agent settings declaring 3 hook events (SessionStart, PreToolUse, PostToolUse).
Skill Claude CodeCodex
Use before searching, reading, or editing files in this repo (or any repo with a "calm" MCP server), or whenever unsure which CALM tool fits — a self-triggerable orientation to the CALM Stage 1-8 tool workflow (repooverview → locate → source → callers → editcontext → editsymbol/editlines → diffimpact →…
Skill Claude CodeCodex
AI-executable audit orchestration OS. Orchestrates specialist frameworks (STRIDE, ATAM, FMEA, MAESTRO, OWASP, SAMM, NIST AI RMF) into evidence-gated, bias-controlled, cycle-learning workflows. Use for: audit this, review this, find gaps, pre-mortem, root cause, security review, architecture review, what am I missing…
MCP server Claude CodeCodexCursor +2
MCP server "hex-graph" as configured in Eilodon/CALM. Launched with hex-graph-mcp.
MCP server Claude CodeCodexCursor +2
MCP server "hex-line" as configured in Eilodon/CALM. Launched with hex-line-mcp.
MCP server Claude CodeCodexCursor +2
Local-first code intelligence for AI agents (MCP). Self-contained — bundles its own runtime. Runs locally from the @colbymchenry/codegraph npm package. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
MCP server "calm" as configured in Eilodon/CALM. Launched with ${CLAUDE_PROJECT_DIR:-.}/scripts/mcp-launcher.sh.
Instructions file CodexOpenCode
AGENTS.md instructions for Eilodon/CALM, covering calm mcp — navigational workflow v2.8, core principles, stage 1 — orient, stage 2 — locate and stage 3 — inspect.
Plugin Claude Code
CALM (Coding Agent Liveness Map) MCP server — call-graph-aware locate/source/editsymbol/diffimpact and 40 tools total, backed by a multi-tier resolver (syntactic -> Stack Graphs -> SCIP) instead of grep. Bundles a SessionStart bootstrap (scaffolds the CALM tool-workflow hook + AGENTS.md into your project on first use.
MCP server Claude CodeCodexCursor +2
MCP server giving coding agents a call-graph-aware, hash-verified view of a codebase, not grep. Runs locally from the @eilodon/calm-mcp npm package.
Skill Claude CodeCodex
Use when implementation is complete, all tests pass, and you are about to merge, create a PR, or close out a development branch — enforces an Architecture Decision Record and PATTERN-DEBT lifecycle review before any integration action.
Skill Claude CodeCodex
Use after a spec document contains SPECAPPROVED=true in its frontmatter, before invoking writing-plans — or when SPECESCALATION=true is set by specialist-review. Runs a FAST risk audit on the design to surface failure modes before any code is written.
Skill Claude CodeCodex
Use when you have a VHEATM audit report and want to extract its findings into Super Skills knowledge — populates Gotchas sections, pattern-debt.md, qbr-calibration.md, and CONTEXT.md from real production audit evidence.
Skill Claude CodeCodex
Use before any feature, component, or behavior change — explores user intent and design before implementation. Precondition: domain-alignment should have run if this is a new project or domain area.
Skill Claude CodeCodex
Use before any software-development task or skill-applicable workflow — classifies task complexity/risk into C0-C4, selects the minimum required Super Skills, preserves evidence discipline across all tiers, and prevents both under-use and over-use of ceremony.
Skill Claude CodeCodex
Use in long sessions, after loading many files, after repeated failed attempts, before phase transitions, or before completion claims — refreshes active goals, skill obligations, evidence anchors, and unresolved T4 assumptions to prevent intra-session instruction drift.
Skill Claude CodeCodex
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies — dispatches one agent per problem domain concurrently.
Skill Claude CodeCodex
Use at the start of a new project, unfamiliar domain, or new product area before brainstorming — creates or updates docs/superskills/CONTEXT.md with vocabulary, actors, invariants, sensitive data, external dependencies, forbidden assumptions, success/failure semantics, and synonyms for KB search.
Skill Claude CodeCodex
Use after brainstorming SPECAPPROVED=true to elevate spec into DPS structure. Creates CONTRACTS.md, BLUEPRINT.md, ADR.md canonical files from approved spec. Also usable standalone to initialize DPS for a new project.
Skill Claude CodeCodex
Use to advance DPS lifecycle status — from DRAFT to PROOF-READY, PROOF-READY to APPROVED-SSOT, or IMPLEMENTATION-ACTIVE to LIVING-SPEC. Runs promotion checklist before advancing.