Skip to main content
Glama

arifOS — Constitutional AI Kernel

by io.github.ariffazil

777 Forge · Execute Gate

arif_forge
Destructive

KERNEL 777 · Execution gate via A-FORGE — mutates only after SEAL verdict.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoengineer
queryNo
plan_idNo
actor_idNo
manifestNo
_envelopeNo
session_idNo
arif_ack_idNo
artifact_idNo
session_tokenNoSCT from arif_init — continuity for ChatGPT multi-call path
vault_entry_idNo
seal_verdict_idNo
ack_irreversibleNo
judge_state_hashNo
approved_action_hashNo
constitutional_chain_idNo

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • addedInput schema / properties / session_token
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "SCT from arif_init — continuity for ChatGPT multi-call path"
+}
  2. Changed2 schema fields changed
    • addedInput schema / properties / approved_action_hash
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
    • addedInput schema / properties / seal_verdict_id
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}
  3. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -{
-  "additionalProperties": true,
-  "type": "object"
-}New value: +null
  4. Added

TDQS

C2.3/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds that mutation occurs 'only after SEAL verdict,' which provides some behavioral context beyond the annotations' destructiveHint. However, it does not elaborate on what mutation entails, what gets affected, or any side effects. Given annotations already indicate destruction, this is marginal improvement.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise (single sentence), but it sacrifices clarity and completeness. While brevity is valued, essential information is missing, making it less useful than a slightly longer but more informative description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's high complexity (16 parameters, no output schema, cryptic sibling names), the description is completely inadequate. It does not explain the tool's purpose in practical terms, the meaning of modes, or how to use it effectively, leaving major gaps for an AI agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With only 6% schema description coverage, the description fails to compensate by explaining any of the 16 parameters. Only one parameter (session_token) has a schema description. The tool description adds no parameter meaning, leaving the agent with minimal guidance for correct invocation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description indicates it is an execution gate that mutates only after a SEAL verdict, but the purpose is vague and does not clearly explain what the tool does concretely. The cryptic phrasing 'KERNEL 777 · Execution gate via A-FORGE' lacks specificity, though it does mention a verb-resource relation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus its siblings (arif_init, arif_judge, etc.) or any context for appropriate invocation. There are no 'when-not-to-use' or alternative suggestions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All arifOS — Constitutional AI Kernel toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

C2.8/5.0
Disambiguation4/5

Each tool targets a distinct kernel function: initialization, observation, reasoning, judgment, routing, execution, memory, and sealing. The abstract descriptions could cause slight confusion, but the KERNEL labels and verb-noun distinctions make roles reasonably clear.

Naming Consistency4/5

All tools share the 'arif_' prefix and are mostly single verbs (init, observe, think, judge, route, forge, seal) but 'memory' is a noun, breaking the pattern slightly. Naming is otherwise consistent and predictable.

Tool Count5/5

Eight tools provide a well-scoped surface for a constitutional AI kernel, covering initiation, perception, reasoning, arbitration, execution, memory, and immutable sealing. The count feels appropriate for the stated purpose without redundancy or bloat.

Completeness4/5

The kernel covers the core lifecycle: init, observe, think, judge, act, and store. Minor gaps exist, such as the absence of a tool for updating or amending constitutional rules, but the primary workflows are supported.

Resources