← Atbash SafetyCONTENT HISTORY

Update to Atbash Safety

Snapshot Nov 22, 2026 · 12:12 UTC · version 0.3.5

Collection source: downloaded plugin package.

WHAT CHANGED

Payment or plan references changed

Full description — Now says: Make an approved change to an existing Atbash agent from Codex. Use when the user wants to change an agent name, purpose, risk, or active state, or...

Observed in published text. Live prices and checkout terms have not been verified by this change.

Save Atbash Safety and check future changes in Following.

Up to 3 plugins free · no card required.

All fields and original values.

Full description

Before

Nov 2, 2026 · 12:47 UTC

Prepare and obtain browser approval for a change to an existing Atbash agent's name, purpose, risk, or active state.

After

Nov 22, 2026 · 12:12 UTC

Make an approved change to an existing Atbash agent from Codex. Use when the user wants to change an agent name, purpose, risk, or active state, or explicitly requests a new Atbash management authorization.

Skill instructions

Before

Nov 2, 2026 · 12:47 UTC

Prepare and obtain browser approval for a change to an existing Atbash agent's name, purpose, risk, or active state. Use Node.js 22.13.0 or newer in a local desktop thread. Resolve `<skill-directory>` to this file's directory and run: ``...

After

Nov 22, 2026 · 12:12 UTC

Make an approved change to an existing Atbash agent from Codex. Use when the user wants to change an agent name, purpose, risk, or active state, or explicitly requests a new Atbash management authorization. Every on-chain change requires...

Supporting files

Before

Nov 2, 2026 · 12:47 UTC

[{"relative_path":"agents/openai.yaml","size_in_bytes":208},{"relative_path":"scripts/atbash-control.mjs","size_in_bytes":551}]

After

Nov 22, 2026 · 12:12 UTC

[{"relative_path":"agents/openai.yaml","size_in_bytes":233},{"relative_path":"scripts/atbash-control.mjs","size_in_bytes":551}]

Compare saved observations

Download comparison JSON

SKILL.md text changes

− removed · + added

--- before
+++ after
@@ -1,38 +1,20 @@
 ---
 name: atbash-manage
-description: Prepare and obtain browser approval for a change to an existing Atbash agent's name, purpose, risk, or active state.
+description: Make an approved change to an existing Atbash agent from Codex. Use when the user wants to change an agent name, purpose, risk, or active state, or explicitly requests a new Atbash management authorization.
 ---
 
 # Atbash Management
 
-Use Node.js 22.13.0 or newer in a local desktop thread. Resolve `<skill-directory>` to this file's directory and run:
+Every on-chain change requires a fresh browser authorization. A prior setup, active profile, existing browser login, or agent private key does not authorize a new owner-level mutation.
 
-```text
-node <skill-directory>/scripts/atbash-control.mjs manage start --host codex
-```
+Start `manage start --host codex` through this skill's `scripts/atbash-control.mjs` launcher. Show the verification URL and code, then inspect the job after wallet verification. Build a non-secret plan JSON with one exact `update_agent` action using the discovered organization, network, and agent public key plus only the fields the user asked to change. Submit it with `manage plan <job-id> --input <path>` through the launcher.
 
-Show the returned verification URL and code. After the user verifies their wallet, run `manage inspect <job-id>` through the same launcher. Use discovery to identify the exact agent and organization; clarify an ambiguous target.
+The helper runs outside the Codex sandbox: inside it, even with network access granted, its DNS lookups fail. Run every launcher command, from the first one, with `sandbox_permissions` set to `"require_escalated"`, a one-sentence `justification` saying the Atbash management helper needs to reach Atbash outside the sandbox, and `prefix_rule` set to `["node", "<skill-directory>/scripts/atbash-control.mjs"]` with the same absolute launcher path as the command. If the shell tool has no `sandbox_permissions` parameter, Codex is already running without a sandbox: run the command as usual. If Codex rejects the escalation because its approval policy never asks, tell the user to switch Codex's permissions to Full access with `/permissions`. A helper error that says Atbash "could not be reached" means the command ran inside the sandbox, not that the service is down.
 
-Create a non-secret plan file with exactly one `update_agent` action:
+The user reviews and signs the exact change in Connect Atbash. Do not click approval controls or sign for them. Inspect and continue until the receipt is complete. If any approved step partially completed, report it and start a new management session for further work.
 
-```json
-{
-  "actions": [
-    {
-      "type": "update_agent",
-      "network": "public",
-      "organization": "<discovered organization>",
-      "agentPubkey": "<discovered public key>",
-      "changes": { "purpose": "<user-requested purpose>" }
-    }
-  ]
-}
-```
+If the user wants to stop before signing, run `manage cancel <job-id>` through the launcher: it cancels the authorization, so its link stops working, and deletes the job's local files. Run it too when the session was cancelled, rejected, or expired; if the helper reports that the session had already ended, the cleanup still succeeded. Do not cancel after the user signed the change; let it finish and report the receipt.
 
-Use the discovered network and identity. Include only requested fields in `changes`: `name`, `purpose`, `risk` (`low`, `medium`, `high`, `critical`), or `active` (boolean). Submit with `manage plan <job-id> --input <path>` through the launcher.
+Supported changes are agent `name`, `purpose`, `risk`, and `active`. Billing upgrades, ownership transfer, key rotation/recovery, certification, policies, mandate, and accountability require their dedicated dashboard flows until the control API explicitly advertises those actions.
 
-The user reviews and signs the exact change in Connect Atbash. Never click approval controls or sign for them. A prior setup or management authorization does not authorize a new change. Inspect the job after approval; when execution is complete, run `manage continue <job-id>` and report its result. A management completion requires no new agent key or profile activation. On partial completion, report completed and failed steps; further changes need a new session and approval.
-
-Use `manage cancel <job-id>` when the user asks to cancel. Stop on expiry or terminal failure. Do not create replacement mutation sessions without the user's intent to continue.
-
-Policy editing, billing, ownership transfer, key recovery, and certification use their dedicated dashboard flows. Never read, print, transmit, or request an agent private key.
+Never read, print, transmit, or ask for an agent private key. Agent keys authorize ordinary Atbash activity only; they do not grant organization-owner permission.
Full technical diff · 3 changed fields

changed /description

BEFORE
"Prepare and obtain browser approval for a change to an existing Atbash agent's name, purpose, risk, or active state."
AFTER
"Make an approved change to an existing Atbash agent from Codex. Use when the user wants to change an agent name, purpose, risk, or active state, or explicitly requests a new Atbash management authorization."

changed /included_files

BEFORE
[
  {
    "relative_path": "agents/openai.yaml",
    "size_in_bytes": 208
  },
  {
    "relative_path": "scripts/atbash-control.mjs",
    "size_in_bytes": 551
  }
]
AFTER
[
  {
    "relative_path": "agents/openai.yaml",
    "size_in_bytes": 233
  },
  {
    "relative_path": "scripts/atbash-control.mjs",
    "size_in_bytes": 551
  }
]

changed /skill_md_contents

BEFORE
"---\nname: atbash-manage\ndescription: Prepare and obtain browser approval for a change to an existing Atbash agent's name, purpose, risk, or active state.\n---\n\n# Atbash Management\n\nUse Node.js 22.13.0 or newer in a local desktop thread. Resolve `<skill-directory>` to this file's directory and run:\n\n```text\nnode <skill-directory>/scripts/atbash-control.mjs manage start --host codex\n```\n\nShow the returned verification URL and code. After the user verifies their wallet, run `manage inspect <job-id>` through the same launcher. Use discovery to identify the exact agent and organization; clarify an ambiguous target.\n\nCreate a non-secret plan file with exactly one `update_agent` action:\n\n```json\n{\n  \"actions\": [\n    {\n      \"type\": \"update_agent\",\n      \"network\": \"public\",\n      \"organization\": \"<discovered organization>\",\n      \"agentPubkey\": \"<discovered public key>\",\n      \"changes\": { \"purpose\": \"<user-requested purpose>\" }\n    }\n  ]\n}\n```\n\nUse the discovered network and identity. Include only requested fields in `changes`: `name`, `purpose`, `risk` (`low`, `medium`, `high`, `critical`), or `active` (boolean). Submit with `manage plan <job-id> --input <path>` through the launcher.\n\nThe user reviews and signs the exact change in Connect Atbash. Never click approval controls or sign for them. A prior setup or management authorization does not authorize a new change. Inspect the job after approval; when execution is complete, run `manage continue <job-id>` and report its result. A management completion requires no new agent key or profile activation. On partial completion, report completed and failed steps; further changes need a new session and approval.\n\nUse `manage cancel <job-id>` when the user asks to cancel. Stop on expiry or terminal failure. Do not create replacement mutation sessions without the user's intent to continue.\n\nPolicy editing, billing, ownership transfer, key recovery, and certification use their dedicated dashboard flows. Never read, print, transmit, or request an agent private key.\n"
AFTER
"---\nname: atbash-manage\ndescription: Make an approved change to an existing Atbash agent from Codex. Use when the user wants to change an agent name, purpose, risk, or active state, or explicitly requests a new Atbash management authorization.\n---\n\n# Atbash Management\n\nEvery on-chain change requires a fresh browser authorization. A prior setup, active profile, existing browser login, or agent private key does not authorize a new owner-level mutation.\n\nStart `manage start --host codex` through this skill's `scripts/atbash-control.mjs` launcher. Show the verification URL and code, then inspect the job after wallet verification. Build a non-secret plan JSON with one exact `update_agent` action using the discovered organization, network, and agent public key plus only the fields the user asked to change. Submit it with `manage plan <job-id> --input <path>` through the launcher.\n\nThe helper runs outside the Codex sandbox: inside it, even with network access granted, its DNS lookups fail. Run every launcher command, from the first one, with `sandbox_permissions` set to `\"require_escalated\"`, a one-sentence `justification` saying the Atbash management helper needs to reach Atbash outside the sandbox, and `prefix_rule` set to `[\"node\", \"<skill-directory>/scripts/atbash-control.mjs\"]` with the same absolute launcher path as the command. If the shell tool has no `sandbox_permissions` parameter, Codex is already running without a sandbox: run the command as usual. If Codex rejects the escalation because its approval policy never asks, tell the user to switch Codex's permissions to Full access with `/permissions`. A helper error that says Atbash \"could not be reached\" means the command ran inside the sandbox, not that the service is down.\n\nThe user reviews and signs the exact change in Connect Atbash. Do not click approval controls or sign for them. Inspect and continue until the receipt is complete. If any approved step partially completed, report it and start a new management session for further work.\n\nIf the user wants to stop before signing, run `manage cancel <job-id>` through the launcher: it cancels the authorization, so its link stops working, and deletes the job's local files. Run it too when the session was cancelled, rejected, or expired; if the helper reports that the session had already ended, the cleanup still succeeded. Do not cancel after the user signed the change; let it finish and report the receipt.\n\nSupported changes are agent `name`, `purpose`, `risk`, and `active`. Billing upgrades, ownership transfer, key rotation/recovery, certification, policies, mandate, and accountability require their dedicated dashboard flows until the control API explicitly advertises those actions.\n\nNever read, print, transmit, or ask for an agent private key. Agent keys authorize ordinary Atbash activity only; they do not grant organization-owner permission.\n"
Full snapshot data
{
  "description": "Make an approved change to an existing Atbash agent from Codex. Use when the user wants to change an agent name, purpose, risk, or active state, or explicitly requests a new Atbash management authorization.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 233
    },
    {
      "relative_path": "scripts/atbash-control.mjs",
      "size_in_bytes": 551
    }
  ],
  "name": "atbash-manage",
  "skill_md_contents": "---\nname: atbash-manage\ndescription: Make an approved change to an existing Atbash agent from Codex. Use when the user wants to change an agent name, purpose, risk, or active state, or explicitly requests a new Atbash management authorization.\n---\n\n# Atbash Management\n\nEvery on-chain change requires a fresh browser authorization. A prior setup, active profile, existing browser login, or agent private key does not authorize a new owner-level mutation.\n\nStart `manage start --host codex` through this skill's `scripts/atbash-control.mjs` launcher. Show the verification URL and code, then inspect the job after wallet verification. Build a non-secret plan JSON with one exact `update_agent` action using the discovered organization, network, and agent public key plus only the fields the user asked to change. Submit it with `manage plan <job-id> --input <path>` through the launcher.\n\nThe helper runs outside the Codex sandbox: inside it, even with network access granted, its DNS lookups fail. Run every launcher command, from the first one, with `sandbox_permissions` set to `\"require_escalated\"`, a one-sentence `justification` saying the Atbash management helper needs to reach Atbash outside the sandbox, and `prefix_rule` set to `[\"node\", \"<skill-directory>/scripts/atbash-control.mjs\"]` with the same absolute launcher path as the command. If the shell tool has no `sandbox_permissions` parameter, Codex is already running without a sandbox: run the command as usual. If Codex rejects the escalation because its approval policy never asks, tell the user to switch Codex's permissions to Full access with `/permissions`. A helper error that says Atbash \"could not be reached\" means the command ran inside the sandbox, not that the service is down.\n\nThe user reviews and signs the exact change in Connect Atbash. Do not click approval controls or sign for them. Inspect and continue until the receipt is complete. If any approved step partially completed, report it and start a new management session for further work.\n\nIf the user wants to stop before signing, run `manage cancel <job-id>` through the launcher: it cancels the authorization, so its link stops working, and deletes the job's local files. Run it too when the session was cancelled, rejected, or expired; if the helper reports that the session had already ended, the cleanup still succeeded. Do not cancel after the user signed the change; let it finish and report the receipt.\n\nSupported changes are agent `name`, `purpose`, `risk`, and `active`. Billing upgrades, ownership transfer, key rotation/recovery, certification, policies, mandate, and accountability require their dedicated dashboard flows until the control API explicitly advertises those actions.\n\nNever read, print, transmit, or ask for an agent private key. Agent keys authorize ordinary Atbash activity only; they do not grant organization-owner permission.\n"
}

SHA-256 of public snapshot: 3fc63e9bd8b1ea5b6231a70a0a837895538aa9e822df205fdf7ede95e1c91d93