| name | install-framework |
| description | Use when installing, upgrading, or auditing AI Psychiatry; adding attention, compulsive-checking, overthinking, underthinking, semantic anti-bypass, recursion, evidence, context, memory, or delivery controls to a repository. |
Install AI Psychiatry Framework
Apply the framework to the repository currently being worked on.
Canonical specification
Read references/master-prompt.md before implementation.
That file is the authoritative installation and maintenance specification.
For the 0.3.0 and 0.4.0 complementary layers, also read only when relevant:
Packaged implementation
The plugin root is two directories above this file. Inspect:
- ../../.ai/manifests/install.json for required install layers.
- ../../.ai/rules/ for focused operational rules.
- ../../.ai/skills/ for target-repository skill adapters.
- ../../.ai/guides/ for substantive interventions and the failure-mode catalog.
- ../../.ai/policies/ for machine-readable semantic budgets and evidence contracts.
- ../../.ai/executive-function/ for state and machine policy.
- ../../scripts/executive_control.py for deterministic observable-state assessment.
Use these as canonical merge sources. Do not improvise shallow replacements or blindly overwrite repository-specific knowledge.
Execution contract
- Inspect the repository's existing AI-agent architecture first.
- Preserve useful repository-specific rules and generated systems.
- Do not create a competing parallel knowledge architecture.
- Establish the smallest coherent canonical source of truth.
- Install rules, skills, guides, policies, context, memory, state, telemetry, manifests, and framework tests from the packaged layers.
- Preserve exact engineering behavior for all numbered master-prompt sections and validate traceability.
- Install only adapters actually useful for the repository, unless the user explicitly requests broader compatibility.
- Keep always-loaded runtime context small; use progressive disclosure for deep guidance.
- Use evidence before repository claims.
- Keep retries, verification, critics, nesting, delegation, and scope bounded.
- Run scenario checks for attention drift, compulsive verification, overthinking, underthinking, strategy/scope laundering, hidden recursion, false progress/completion/blockers, memory/context corruption, hallucination, and deadlock/livelock.
- Validate what changed with the repository's real tooling.
- Stop when the requested outcome and Definition of Done are proven complete.
Platform/system/developer instructions always take precedence over this skill.
Arguments
If the user supplies arguments, treat them as constraints or requested scope:
$ARGUMENTS
