integrity-self-monitoring

v0.1.2

Real-result discipline for work that cannot be done as asked. When a service cannot be reached, a key is missing or two tests want different answers, the easy route is a result that only looks done: a fallback that returns made-up values, a table standing in for the service, code that answers its caller differently, a machine changed until the run goes green. Bundles the integrity-self-monitoring skill (the 'what': the result must be real and the route to it legitimate; "cannot be done as asked, because X" is a complete answer; close with an [INTEGRITY CHECK] - Result, Route, Outside the task, Told the user) with per-host hooks (the 'when') that read each edit to product code for those shapes - only in a file that calls a service - and each shell command for a change to the machine or a server started, and say what it means for the user once per finding. No message on the prompt. Never blocks. Codex: the same hooks/ adapter as Claude Code - same events, same payload, same output envelope; the hooks run once you trust them with /hooks.

CodexClaude Code1 Skill

By David GiordanoLicense: Apache-2.01 GitHub starsUpdated 1 hour ago

Directory evidence

Runtimes: Codex and Claude Code
Parsed components: 1 skill or MCP entry
Source updated: Sep 29, 2026
Manifest status: Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install integrity-self-monitoring for Codex and Claude Code

Installs for the current user

codex plugin marketplace add 3dgiordano/agent-plugins
codex plugin marketplace upgrade 3dgiordano-agent-plugins
codex plugin add integrity-self-monitoring@3dgiordano-agent-plugins

Paste and run these commands in a terminal with Codex. They add and refresh the 3dgiordano-agent-plugins catalog, then install this plugin.

Compatibility: the page URL and API slug “integrity-self-monitoring” remain stable.

Codex: integrity-self-monitoring@agent-plugin-marketplace → integrity-self-monitoring@3dgiordano-agent-plugins

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually

$ git clone https://github.com/3dgiordano/agent-plugins

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The plugin root is plugins/integrity-self-monitoring/.

Plugin files

plugins/integrity-self-monitoring/

├── .codex-plugin/plugin.json
├── .claude-plugin/plugin.json
└── skills/integrity-self-monitoring/SKILL.md

Included Skills1

integrity-self-monitoringskills/integrity-self-monitoring/SKILL.md

Real-result discipline for work that cannot be done as asked. When a service cannot be reached, a key is missing or two tests want different answers, the easy route is a result that only looks done - a fallback that returns made-up values, a table standing in for the service, code that answers its caller differently, a machine changed until the run goes green - reported as the fix. This skill keeps the result real and the route to it legitimate, makes 'cannot be done as asked, because X' a complete answer, and closes with an [INTEGRITY CHECK]: Result, Route, Outside the task, Told the user. Triggers - fallback, default value, hard-coded rates, offline data, mock the service, service unreachable, no API key, missing credentials, make the tests pass, tests green, workaround, disable TLS, hosts file, local server, stand-in, tests that contradict each other, cannot be done.

Plugin manifests2

plugins/integrity-self-monitoring/.codex-plugin/plugin.json

{
  "name": "integrity-self-monitoring",
  "version": "0.1.2",
  "description": "Real-result discipline for work that cannot be done as asked. When a service cannot be reached, a key is missing or two tests want different answers, the easy route is a result that only looks done: a fallback that returns made-up values, a table standing in for the service, code that answers its caller differently, a machine changed until the run goes green. Bundles the integrity-self-monitoring skill (the 'what': the result must be real and the route to it legitimate; \"cannot be done as asked, because X\" is a complete answer; close with an [INTEGRITY CHECK] - Result, Route, Outside the task, Told the user) with per-host hooks (the 'when') that read each edit to product code for those shapes - only in a file that calls a service - and each shell command for a change to the machine or a server started, and say what it means for the user once per finding. No message on the prompt. Never blocks. Codex: the same hooks/ adapter as Claude Code - same events, same payload, same output envelope; the hooks run once you trust them with /hooks.",
  "author": {
    "name": "David Giordano",
    "url": "https://github.com/3dgiordano"
  },
  "homepage": "https://github.com/3dgiordano/agent-plugins/tree/main/plugins/integrity-self-monitoring",
  "repository": "https://github.com/3dgiordano/agent-plugins",
  "license": "Apache-2.0",
  "keywords": [
    "integrity",
    "self-monitoring",
    "fallback",
    "made-up-data",
    "shortcut",
    "real-result",
    "honest-failure",
    "agent-loop"
  ],
  "skills": "./skills/",
  "hooks": "./hooks/hooks.json"
}

plugins/integrity-self-monitoring/.claude-plugin/plugin.json

{
  "name": "integrity-self-monitoring",
  "version": "0.1.2",
  "description": "Real-result discipline for work that cannot be done as asked. When a service cannot be reached, a key is missing or two tests want different answers, the easy route is a result that only looks done: a fallback that returns made-up values, a table standing in for the service, code that answers its caller differently, a machine changed until the run goes green. Bundles the integrity-self-monitoring skill (the 'what': the result must be real and the route to it legitimate; \"cannot be done as asked, because X\" is a complete answer; close with an [INTEGRITY CHECK] - Result, Route, Outside the task, Told the user) with per-host hooks (the 'when') that read each edit to product code for those shapes - only in a file that calls a service - and each shell command for a change to the machine or a server started, and say what it means for the user once per finding. No message on the prompt. Never blocks. Claude Code: PostToolUse reader on every tool; Stop reads the close for the block and a dispute, which the user sees as one line.",
  "author": {
    "name": "David Giordano",
    "url": "https://github.com/3dgiordano"
  },
  "homepage": "https://github.com/3dgiordano/agent-plugins/tree/main/plugins/integrity-self-monitoring",
  "repository": "https://github.com/3dgiordano/agent-plugins",
  "documentationUrl": "https://github.com/3dgiordano/agent-plugins/tree/main/plugins/integrity-self-monitoring#readme",
  "supportUrl": "https://github.com/3dgiordano/agent-plugins/issues",
  "privacyPolicyUrl": "https://github.com/3dgiordano/agent-plugins/blob/main/SECURITY.md",
  "license": "Apache-2.0",
  "keywords": [
    "integrity",
    "self-monitoring",
    "fallback",
    "made-up-data",
    "shortcut",
    "real-result",
    "honest-failure",
    "agent-loop"
  ]
}

Browse the “integrity” tag →

makoto

by Clear-Sights

Holds Claude Code to its word — every claim checked against the agent's own logged record; faked checks blocked, not warned. Two-tier catalog (36 pre-checks, 26 Stop gates), each shipped at measured zero false positives.

Claude Code

45Updated yesterday

skill-provenance

by PAICE.work PBC

Version, validate, bootstrap, package, verify, and hand off portable Agent Skill bundles.

CodexClaude Code5 Skills

7Updated 5 days ago

integrity-self-monitoring

by David Giordano

Real-result discipline for work that cannot be done as asked. When a service cannot be reached, a key is missing or two tests want different answers, the easy route is a result that only looks done: a fallback that returns made-up values, a table standing in for the service, code that answers its caller differently, a machine changed until the run goes green. Bundles the integrity-self-monitoring skill (the 'what': the result must be real and the route to it legitimate; "cannot be done as asked, because X" is a complete answer; close with an [INTEGRITY CHECK] - Result, Route, Outside the task, Told the user) with per-host hooks (the 'when') that read each edit to product code for those shapes - only in a file that calls a service - and each shell command for a change to the machine or a server started, and say what it means for the user once per finding. No message on the prompt. Never blocks. Portable core: the skill only; hooks are host-specific (hooks/ for Claude Code and Codex, cursor/ for Cursor).

Agent Plugins

1Updated 1 hour ago

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[integrity-self-monitoring on Agent Plugins Marketplace](https://pluginsmp.com/plugins/integrity-self-monitoring)