chatgpt-esra
v0.4.1Evidence-driven ESRA improvement workflows and a local Codex runtime.
By rrpaulsLicense: Apache-2.01 GitHub starsUpdated 3 hours ago
Directory evidence
- Runtimes
- Codex and Agent Plugins
- Parsed components
- 5 skill or MCP entries
- Source updated
- Sep 24, 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 chatgpt-esra for Codex
codex plugin marketplace add rrpauls/chatgpt-esra
codex plugin marketplace upgrade esra
codex plugin add chatgpt-esra@esraPaste and run these commands in a terminal with Codex. They add and refresh the esra catalog, then install this plugin.
Compatibility: the page URL and API slug “chatgpt-esra” remain stable.
- Codex:
chatgpt-esra@agent-plugin-marketplace→chatgpt-esra@esra
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/rrpauls/chatgpt-esraClone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.
Plugin files
├── .codex-plugin/plugin.json├── plugin.json├── skills/esra-crisis/SKILL.md├── skills/esra-decisions/SKILL.md├── skills/esra-experiments/SKILL.md├── skills/esra-orchestrator/SKILL.md└── skills/esra-reflection/SKILL.md
Included Skills5
Triage active incidents and build resilience after failures using containment, recovery, and controlled tests. Skip ordinary debugging without urgent impact.
Structure consequential choices under uncertainty using OODA, trade-offs, and system feedback. Skip straightforward factual or syntax questions.
Design bounded tests of proposed workflow or architecture improvements with baselines and rollback. Not required for ordinary test execution.
Run bounded ESRA reviews after major architecture or skill changes, repeated failures, or an explicit full-cycle request. Skip routine work.
Review recurring errors or completed experiments and turn supported lessons into minimal workflow updates. Audit recorded ESRA cycles on request.
Plugin manifests2
{
"name": "chatgpt-esra",
"version": "0.4.1",
"description": "Evidence-driven ESRA improvement workflows and a local Codex runtime.",
"author": {
"name": "rrpauls",
"url": "https://github.com/rrpauls"
},
"homepage": "https://github.com/rrpauls/chatgpt-esra",
"repository": "https://github.com/rrpauls/chatgpt-esra",
"license": "Apache-2.0",
"keywords": [
"esra",
"codex",
"chatgpt",
"decision-making",
"experiments"
],
"skills": "./skills/",
"interface": {
"displayName": "ESRA for OpenAI",
"shortDescription": "Bounded improvement cycles for ChatGPT and Codex",
"longDescription": "Five selective ESRA skills plus a local, privacy-preserving Codex runtime for evidence logs, baselines, experiments, audits, validation, and lifecycle signals.",
"developerName": "rrpauls",
"category": "Developer Tools",
"capabilities": [
"Analysis",
"Local automation"
],
"websiteURL": "https://github.com/rrpauls/chatgpt-esra",
"composerIcon": "./assets/logo-openai.png",
"logo": "./assets/logo-openai.png",
"logoDark": "./assets/logo-openai.png",
"defaultPrompt": [
"Review this major change with one bounded ESRA cycle.",
"Design a reversible experiment for this improvement.",
"Audit my recorded ESRA cycles for recurring problems."
]
}
}{
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
"name": "chatgpt-esra",
"version": "0.4.1",
"description": "Evidence-driven ESRA improvement workflows for ChatGPT and Codex.",
"author": {
"name": "rrpauls",
"url": "https://github.com/rrpauls"
},
"homepage": "https://github.com/rrpauls/chatgpt-esra",
"repository": "https://github.com/rrpauls/chatgpt-esra",
"license": "Apache-2.0",
"keywords": [
"esra",
"codex",
"chatgpt",
"decision-making",
"experiments"
],
"extensions": {
"com.openai": {
"hooks": "./hooks/hooks.json",
"interface": {
"displayName": "ESRA for OpenAI",
"shortDescription": "Bounded improvement cycles for ChatGPT and Codex",
"longDescription": "Five selective ESRA skills plus a local, privacy-preserving runtime for evidence logs, baselines, experiments, audits, validation, and lifecycle signals.",
"developerName": "rrpauls",
"category": "Developer Tools",
"capabilities": [
"Analysis",
"Local automation"
],
"websiteURL": "https://github.com/rrpauls/chatgpt-esra",
"composerIcon": "./assets/logo-openai.png",
"logo": "./assets/logo-openai.png",
"logoDark": "./assets/logo-openai.png",
"defaultPrompt": [
"Review this major change with one bounded ESRA cycle.",
"Design a reversible experiment for this improvement.",
"Audit my recorded ESRA cycles for recurring problems."
]
}
}
}
}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.
[chatgpt-esra on Agent Plugins Marketplace](https://pluginsmp.com/plugins/chatgpt-esra)