Intrikata Stack guide · package 1.7.1

Harness compatibility map

Human-readable guide · view canonical Markdown · updated 2026-08-26

HARNESS.md — executing the intrikata-stack skills outside Claude Code

The skill files in this package are written in Claude Code's skill dialect, but they are procedures, not plugins: any agentic code builder that can read files and run shell commands can execute them. This document maps every Claude-Code-specific primitive the skill bodies mention to its generic equivalent.

The guarantee

The skills' filesystem-fallback path uses only two capabilities: shell execution and file reads — capabilities every code-builder agent has. Everything beyond that (graph backend, MCP tools, typed subagents) is an optional enrichment with an explicit in-skill fallback. When in doubt, take the fallback branch; the skills treat it as a designed mode, never an error.

Primitive map

Claude Code primitive in the skill text	Your equivalent
Skill invocation (`/megapraxis`, `Skill` tool)	read `skills/megapraxis/SKILL.md` and execute it top-to-bottom
in-context skill listing ("harness truth")	your own tool/instruction inventory; if you can't enumerate one, verify by file presence on disk
`ToolSearch select:mcp__…` (MCP tool probe)	check whether your harness has that tool registered; if you have no MCP support, the probe "fails" — take the documented filesystem-fallback
`AskUserQuestion` (structured options)	ask the user in chat with the same options
`Agent(subagent_type=…)` dispatch	your subtask / parallel-agent mechanism; if you have none, execute the member's instructions inline, sequentially
`TodoWrite` / task tracking	your todo mechanism, or a plain checklist in your reply
SessionStart hook auto-fire	run megapraxis when a session begins or when the user asks to be oriented
`~/.claude/skills/`, `enabledPlugins`, plugin registries	Claude-Code-specific inventory surfaces; when the skill audits them and they don't exist on your machine, report them absent — do not fabricate
MCP graph backend (`megapraxis_boot`, node CRUD)	optional — see BACKEND.md; without it, both skills run in filesystem mode
OpenAI Codex plugin / `~/.codex/skills`	prefer the native marketplace in `ONBOARD-CODEX.md`; direct fallback is `install.py --harness codex`; invoke `$praxis:megapraxis` as a plugin or `$megapraxis` as a direct skill
Optional backend assistant op	`CodexCode_v1` parallels `ClaudeCode_v1`; `codex exec` keeps subscription auth, while an unavailable-CLI fallback may use the official OpenAI CLI with child-scoped `CODEXCODE_OPENAI_API_KEY`
Grok Build session / `~/.grok/skills`	install with `install.py --target ~/.grok/skills`; follow https://docs.intrikata.com/onboard-grok.md short-circuit (no MCP required); adapter `adapters/GROK.md`

OpenAI Codex short-circuit

Install the native intrikata-stack plugin once, verify it in a new Codex task, then reuse it from every future project. On orientation-only requests, run Megapraxis and stop; do not pay the full Metamegapraxis swarm cost unless the user asks for an audit or a blocking trap is detected.

Follow ONBOARD-CODEX.md or https://docs.intrikata.com/onboard-codex.md.
Prefer the served Codex marketplace; use install.py --harness codex only as a direct-skill fallback.
Map ToolSearch to Codex's current tool registry and Agent(subagent_type=...) to Codex's

multi-agent mechanism. Exact tool prefixes are harness-owned; discover them rather than copying Claude's mcp__plugin_* spelling.

Treat absent graph tools as optional during orientation. Preserve traps #4/#5 only when the

user requested graph-backed features or a declared server should be live.

This is bridge-class onboarding-short-circuit: it removes repeated setup, not future audits. Novel work and explicit Metamegapraxis swarm requests still pay full cost.

Grok Build short-circuit

New Grok projects should not pay full MetaMethodology swarm cost to onboard. Sequence:

Read onboard-grok.md / demo/grok-onboard.json (live on docs.intrikata.com).
Install skills once into ~/.grok/skills (and/or ~/.claude/skills if shared).
Run megapraxis filesystem-fallback only; skip swarm until explicit user dispatch.
Treat traps #4/#5 (MCP launch) as N/A on pure Grok orientation unless graph features are in scope.

That is an onboarding short-circuit (bridge-class onboarding-short-circuit), not a claim that self-audit is free forever. Novel audits still pay full price.

What to expect per skill

megapraxis — emits a session-start briefing. Outside Claude Code, mode detection and the

disk-verified inventory work as written (they are shell + file reads); the plugin/MCP audit sections will mostly report "not applicable on this harness," which is the truthful output.

metamegapraxis — audits megapraxis. The trap roll-call's disk probes work anywhere;

graph-backed probes degrade to — with a reason, exactly as the skill specifies.

megametapraxis — measures drift from the last validated metamegapraxis envelope

toward the Tarski limit. The instrument is scripts/drift_hook.py (filesystem-only). Distance to the limit is UNDECIDABLE and must never be a number. After an audit, write the envelope with --snapshot --validated. Hooks close the loop on every prompt / spawn / agent stop; they never invoke the skill.

Honesty rule (applies on every harness)

The skills' core contract is harness-independent: every emitted claim corresponds to a truth on disk; counts are computed or rendered count-skipped; what can't be decided is named, never absorbed. If your harness can't verify something, say so in the output — that is compliant behavior, not failure.