arifOS — Constitutional AI Kernel

777 Forge · Execute Gate

arif_forge

Destructive

Apply an authorized system modification. Requires a valid seal_verdict_id obtained from arif_judge. Mode: dry_run (preview impact without execution), apply (execute authorized change). Outputs: execution receipt.

Input Schema

Name	Required	Description	Default
`mode`	No	'engineer' (default) — plan and apply the work; 'dry_run' — preview what would happen, nothing is applied; 'query' — read-only questions about the workspace; 'write' — write files; 'generate' — generate code or content; 'commit' — commit prepared work; 'recall' — retrieve past forge artifacts.	engineer
`query`	No	The task in plain language when no manifest is supplied, e.g. 'restart the gateway service'.
`plan_id`	No	Plan id from arif_think's plan mode, when executing an approved plan.
`actor_id`	No	Your agent identity, e.g. 'kimi-code/FI-008' — recorded in the audit log.
`manifest`	No	Required for engineer (the default mode), write, and generate: the work order (usually JSON or markdown) describing exactly what to build or change — the more specific, the tighter the gate. mode=dry_run accepts the manifest or a plain-language query; mode=query uses query instead.
`session_id`	No	Session id returned by arif_init; scopes this execution to your governed session.
`arif_ack_id`	No	Acknowledgment id from a prior step, for multi-step execution chains.
`artifact_id`	No	Id of an existing artifact (from an earlier forge or judge response) that this call operates on.
`session_token`	No	Session Continuity Token (SCT) returned by arif_init — proves the session is yours.
`vault_entry_id`	No	Id of the permanent-ledger entry linked to this execution, when one already exists.
`seal_verdict_id`	No	The SEAL verdict id arif_judge returned — without it, nothing is executed.
`ack_irreversible`	No	Set true to confirm you accept this execution cannot be undone, when the judged action was irreversible.
`judge_state_hash`	No	Hash string from the arif_judge SEAL response — proves the verdict has not been tampered with.
`approved_action_hash`	No	Hash of the exact action that was judged — execution is refused if what you submit differs from it.
`constitutional_chain_id`	No	Id of the evidence chain (observe→think→judge) that led to the SEAL — copy it from the judge response.

Output Schema

Name	Required	Description	Default
`meta`	Yes
`tool`	Yes
`result`	Yes
`status`	Yes
`delta_S`	No
`reasons`	Yes
`actor_id`	No
`timestamp`	Yes
`session_id`	No
`nine_signal`	Yes
`output_policy`	No
`stage_progression`	No
`philosophical_anchor`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 18, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "actor_id": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "delta_S": {
+      "anyOf": [
+        {
+          "type": "number"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "meta": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "nine_signal": {
+      "additionalProperties": true,
+      "properties": {
+        "delta": {
+          "properties": {
+            "en": {
+              "type": "string"
+            },
+            "plane": {
+              "type": "string"
+            },
+            "state": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "state",
+            "en"
+          ],
+          "type": "object"
+        },
+        "omega": {
+          "properties": {
+            "en": {
+              "type": "string"
+            },
+            "plane": {
+              "type": "string"
+            },
+            "state": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "state",
+            "en"
+          ],
+          "type": "object"
+        },
+        "overall": {
+          "properties": {
+            "en": {
+              "type": "string"
+            },
+            "state": {
+              "type": "string"
+            }
+          },
+          "type": "object"
+        },
+        "psi": {
+          "properties": {
+            "en": {
+              "type": "string"
+            },
+            "plane": {
+              "type": "string"
+            },
+            "state": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "state",
+            "en"
+          ],
+          "type": "object"
+        }
+      },
+      "type": "object"
+    },
+    "output_policy": {
+      "type": "string"
+    },
+    "philosophical_anchor": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "reasons": {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "result": {
+      "additionalProperties": true,
+      "properties": {
+        "artifact_id": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "execution_trace": {
+          "anyOf": [
+            {
+              "items": {
+                "additionalProperties": true,
+                "type": "object"
+              },
+              "type": "array"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "irreversibility_level": {
+          "type": "string"
+        },
+        "mode": {
+          "type": "string"
+        },
+        "nine_signal": {
+          "additionalProperties": true,
+          "type": "object"
+        },
+        "reasons": {
+          "anyOf": [
+            {
+              "items": {
+                "type": "string"
+              },
+              "type": "array"
+            },
+            {
+              "type": "null"
+            }
+          ]
+        },
+        "status": {
+          "type": "string"
+        },
+        "verdict": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "session_id": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "stage_progression": {
+      "anyOf": [
+        {
+          "type": "null"
+        },
+        {
+          "properties": {
+            "current_stage": {
+              "type": "string"
+            },
+            "next_prompt": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ]
+            },
+            "next_stage": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ]
+            },
+            "next_tool": {
+              "anyOf": [
+                {
+                  "type": "string"
+                },
+                {
+                  "type": "null"
+                }
+              ]
+            }
+          },
+          "type": "object"
+        }
+      ]
+    },
+    "status": {
+      "type": "string"
+    },
+    "timestamp": {
+      "type": "string"
+    },
+    "tool": {
+      "const": "arif_forge"
+    }
+  },
+  "required": [
+    "status",
+    "tool",
+    "result",
+    "meta",
+    "timestamp",
+    "nine_signal",
+    "reasons"
+  ],
+  "type": "object"
+}

Changed1 schema field changedOct 14, 2026

changedInput schema / properties / manifest / description

Previous value: -"Required for engineer (the default mode), write, generate, and dry_run: the work order (usually JSON or markdown) describing exactly what to build or change — the more specific, the tighter the gate. mode=query uses query instead."New value: +"Required for engineer (the default mode), write, and generate: the work order (usually JSON or markdown) describing exactly what to build or change — the more specific, the tighter the gate. mode=dry_run accepts the manifest or a plain-language query; mode=query uses query instead."

Changed2 schema fields changedOct 14, 2026

addedInput schema / allOf

Added value: +[
+  {
+    "if": {
+      "anyOf": [
+        {
+          "not": {
+            "required": [
+              "mode"
+            ]
+          }
+        },
+        {
+          "properties": {
+            "mode": {
+              "enum": [
+                "engineer",
+                "write",
+                "generate"
+              ]
+            }
+          },
+          "required": [
+            "mode"
+          ]
+        }
+      ]
+    },
+    "then": {
+      "required": [
+        "manifest"
+      ]
+    }
+  },
+  {
+    "if": {
+      "properties": {
+        "mode": {
+          "enum": [
+            "dry_run"
+          ]
+        }
+      },
+      "required": [
+        "mode"
+      ]
+    },
+    "then": {
+      "anyOf": [
+        {
+          "required": [
+            "manifest"
+          ]
+        },
+        {
+          "required": [
+            "query"
+          ]
+        }
+      ]
+    }
+  }
+]

changedInput schema / properties / manifest / description

Previous value: -"The work order (usually JSON or markdown) describing exactly what to build or change — the more specific, the tighter the gate."New value: +"Required for engineer (the default mode), write, generate, and dry_run: the work order (usually JSON or markdown) describing exactly what to build or change — the more specific, the tighter the gate. mode=query uses query instead."

Changed1 schema field changedOct 14, 2026

removedInput schema / properties / _envelope

Removed value: -{
-  "default": null,
-  "description": "Internal transport envelope handle — server-side; omit.",
-  "title": "Envelope"
-}

Changed16 schema fields changedOct 1, 2026

addedInput schema / properties / _envelope / description

Added value: +"Internal transport envelope handle — server-side; omit."

addedInput schema / properties / ack_irreversible / description

Added value: +"Set true to confirm you accept this execution cannot be undone, when the judged action was irreversible."

addedInput schema / properties / actor_id / description

Added value: +"Your agent identity, e.g. 'kimi-code/FI-008' — recorded in the audit log."

addedInput schema / properties / approved_action_hash / description

Added value: +"Hash of the exact action that was judged — execution is refused if what you submit differs from it."

addedInput schema / properties / arif_ack_id / description

Added value: +"Acknowledgment id from a prior step, for multi-step execution chains."

addedInput schema / properties / artifact_id / description

Added value: +"Id of an existing artifact (from an earlier forge or judge response) that this call operates on."

addedInput schema / properties / constitutional_chain_id / description

Added value: +"Id of the evidence chain (observe→think→judge) that led to the SEAL — copy it from the judge response."

addedInput schema / properties / judge_state_hash / description

Added value: +"Hash string from the arif_judge SEAL response — proves the verdict has not been tampered with."

addedInput schema / properties / manifest / description

Added value: +"The work order (usually JSON or markdown) describing exactly what to build or change — the more specific, the tighter the gate."

addedInput schema / properties / mode / description

Added value: +"'engineer' (default) — plan and apply the work; 'dry_run' — preview what would happen, nothing is applied; 'query' — read-only questions about the workspace; 'write' — write files; 'generate' — generate code or content; 'commit' — commit prepared work; 'recall' — retrieve past forge artifacts."

addedInput schema / properties / plan_id / description

Added value: +"Plan id from arif_think's plan mode, when executing an approved plan."

addedInput schema / properties / query / description

Added value: +"The task in plain language when no manifest is supplied, e.g. 'restart the gateway service'."

addedInput schema / properties / seal_verdict_id / description

Added value: +"The SEAL verdict id arif_judge returned — without it, nothing is executed."

addedInput schema / properties / session_id / description

Added value: +"Session id returned by arif_init; scopes this execution to your governed session."

changedInput schema / properties / session_token / description

Previous value: -"SCT from arif_init — continuity for ChatGPT multi-call path"New value: +"Session Continuity Token (SCT) returned by arif_init — proves the session is yours."

addedInput schema / properties / vault_entry_id / description

Added value: +"Id of the permanent-ledger entry linked to this execution, when one already exists."

Changed16 schema fields changedOct 1, 2026

removedInput schema / properties / _envelope / description

Removed value: -"Internal transport envelope handle — server-side; omit."

removedInput schema / properties / ack_irreversible / description

Removed value: -"Set true to confirm you accept this execution cannot be undone, when the judged action was irreversible."

removedInput schema / properties / actor_id / description

Removed value: -"Your agent identity, e.g. 'kimi-code/FI-008' — recorded in the audit log."

removedInput schema / properties / approved_action_hash / description

Removed value: -"Hash of the exact action that was judged — execution is refused if what you submit differs from it."

removedInput schema / properties / arif_ack_id / description

Removed value: -"Acknowledgment id from a prior step, for multi-step execution chains."

removedInput schema / properties / artifact_id / description

Removed value: -"Id of an existing artifact (from an earlier forge or judge response) that this call operates on."

removedInput schema / properties / constitutional_chain_id / description

Removed value: -"Id of the evidence chain (observe→think→judge) that led to the SEAL — copy it from the judge response."

removedInput schema / properties / judge_state_hash / description

Removed value: -"Hash string from the arif_judge SEAL response — proves the verdict has not been tampered with."

removedInput schema / properties / manifest / description

Removed value: -"The work order (usually JSON or markdown) describing exactly what to build or change — the more specific, the tighter the gate."

removedInput schema / properties / mode / description

Removed value: -"'engineer' (default) — plan and apply the work; 'dry_run' — preview what would happen, nothing is applied; 'query' — read-only questions about the workspace; 'write' — write files; 'generate' — generate code or content; 'commit' — commit prepared work; 'recall' — retrieve past forge artifacts."

removedInput schema / properties / plan_id / description

Removed value: -"Plan id from arif_think's plan mode, when executing an approved plan."

removedInput schema / properties / query / description

Removed value: -"The task in plain language when no manifest is supplied, e.g. 'restart the gateway service'."

removedInput schema / properties / seal_verdict_id / description

Removed value: -"The SEAL verdict id arif_judge returned — without it, nothing is executed."

removedInput schema / properties / session_id / description

Removed value: -"Session id returned by arif_init; scopes this execution to your governed session."

changedInput schema / properties / session_token / description

Previous value: -"Session Continuity Token (SCT) returned by arif_init — proves the session is yours."New value: +"SCT from arif_init — continuity for ChatGPT multi-call path"

removedInput schema / properties / vault_entry_id / description

Removed value: -"Id of the permanent-ledger entry linked to this execution, when one already exists."

Changed16 schema fields changedSep 25, 2026

addedInput schema / properties / _envelope / description

Added value: +"Internal transport envelope handle — server-side; omit."

addedInput schema / properties / ack_irreversible / description

Added value: +"Set true to confirm you accept this execution cannot be undone, when the judged action was irreversible."

addedInput schema / properties / actor_id / description

Added value: +"Your agent identity, e.g. 'kimi-code/FI-008' — recorded in the audit log."

addedInput schema / properties / approved_action_hash / description

Added value: +"Hash of the exact action that was judged — execution is refused if what you submit differs from it."

addedInput schema / properties / arif_ack_id / description

Added value: +"Acknowledgment id from a prior step, for multi-step execution chains."

addedInput schema / properties / artifact_id / description

Added value: +"Id of an existing artifact (from an earlier forge or judge response) that this call operates on."

addedInput schema / properties / constitutional_chain_id / description

Added value: +"Id of the evidence chain (observe→think→judge) that led to the SEAL — copy it from the judge response."

addedInput schema / properties / judge_state_hash / description

Added value: +"Hash string from the arif_judge SEAL response — proves the verdict has not been tampered with."

addedInput schema / properties / manifest / description

Added value: +"The work order (usually JSON or markdown) describing exactly what to build or change — the more specific, the tighter the gate."

addedInput schema / properties / mode / description

Added value: +"'engineer' (default) — plan and apply the work; 'dry_run' — preview what would happen, nothing is applied; 'query' — read-only questions about the workspace; 'write' — write files; 'generate' — generate code or content; 'commit' — commit prepared work; 'recall' — retrieve past forge artifacts."

addedInput schema / properties / plan_id / description

Added value: +"Plan id from arif_think's plan mode, when executing an approved plan."

addedInput schema / properties / query / description

Added value: +"The task in plain language when no manifest is supplied, e.g. 'restart the gateway service'."

addedInput schema / properties / seal_verdict_id / description

Added value: +"The SEAL verdict id arif_judge returned — without it, nothing is executed."

addedInput schema / properties / session_id / description

Added value: +"Session id returned by arif_init; scopes this execution to your governed session."

changedInput schema / properties / session_token / description

Previous value: -"SCT from arif_init — continuity for ChatGPT multi-call path"New value: +"Session Continuity Token (SCT) returned by arif_init — proves the session is yours."

addedInput schema / properties / vault_entry_id / description

Added value: +"Id of the permanent-ledger entry linked to this execution, when one already exists."

Changed1 schema field changedJul 17, 2026

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"
+}

Changed2 schema fields changedJul 5, 2026

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
+}

Changed1 schema field changedJul 4, 2026

changedOutput schema / (root)

Previous value: -{
-  "additionalProperties": true,
-  "type": "object"
-}New value: +null

AddedJul 3, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare destructiveHint=true, idempotentHint=false, and readOnlyHint=false, so the safety profile is covered. The description adds real context beyond that — the authorization gate and the dry_run preview path — but says nothing about what happens on refusal, what 'impact' a preview returns, or the irreversibility acknowledgment flow.

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

Conciseness4/5

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

Three short, front-loaded sentences with no filler: purpose, precondition, modes, output. Efficient, though the mode sentence is where the inaccuracy was introduced — brevity at the cost of correctness.

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

Completeness3/5

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

For a 15-parameter destructive tool the description is thin, but the schema is fully documented and an output schema exists, so the agent can recover most missing detail. What it cannot recover is the tamper-hash / constitutional-chain requirement, which the prose never mentions.

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

Parameters2/5

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

Schema coverage is 100%, so a baseline of 3 would apply, but the description actively misinforms: it lists 'apply' as a mode when the enum contains engineer/query/write/generate/commit/recall/dry_run and no 'apply'. An agent following the prose would submit an invalid mode. It adds no meaning for the hash, session, or chain parameters.

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

Purpose4/5

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

States a specific verb and resource — 'Apply an authorized system modification' — and distinguishes itself from arif_judge by requiring the verdict that judge produces. The addition of the two modes and the receipt output confirms what kind of operation this is, though the mode list it names is wrong.

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

Usage Guidelines3/5

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

It gives one strong prerequisite: a valid seal_verdict_id from arif_judge, which implies the judge→forge sequence. But it only explains 2 of the 7 modes the schema actually allows, and gives no guidance on when to prefer this over siblings like arif_delegate or arif_seal.

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 tools Inspect

Try in Browser

Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

777 Forge · Execute Gate

Input Schema

Output Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources