openai-docs skill is invoked too aggressively.

What version of Codex CLI is running?

codex-cli 0.154.0

What subscription do you have?

Plus

Which model were you using?

gpt-5.6-sol · xhigh

What platform is your computer?

Linux 7.0.0-31-generic x86_64 unknown

What terminal emulator and version are you using (if applicable)?

No response

Codex doctor report

{
  "schemaVersion": 1,
  "generatedAt": "1789291824s since unix epoch",
  "overallStatus": "warning",
  "codexVersion": "0.154.0",
  "checks": {
    "app_server.status": {
      "id": "app_server.status",
      "category": "app-server",
      "status": "ok",
      "summary": "background server is not running",
      "details": {
        "control socket": "/home/srnissen/.codex/app-server-control/app-server-control.sock",
        "daemon state dir": "/home/srnissen/.codex/app-server-daemon",
        "mode": "ephemeral",
        "pid file": "/home/srnissen/.codex/app-server-daemon/app-server.pid (missing)",
        "settings": "/home/srnissen/.codex/app-server-daemon/settings.json (missing)",
        "status": "not running",
        "update-loop pid file": "/home/srnissen/.codex/app-server-daemon/app-server-updater.pid (missing)"
      },
      "remediation": null,
      "durationMs": 0
    },
    "auth.credentials": {
      "id": "auth.credentials",
      "category": "auth",
      "status": "ok",
      "summary": "auth is configured",
      "details": {
        "auth file": "/home/srnissen/.codex/auth.json",
        "auth storage mode": "File",
        "stored API key": "false",
        "stored ChatGPT tokens": "true",
        "stored agent identity": "false",
        "stored auth mode": "chatgpt"
      },
      "remediation": null,
      "durationMs": 0
    },
    "config.load": {
      "id": "config.load",
      "category": "config",
      "status": "ok",
      "summary": "config loaded",
      "details": {
        "CODEX_HOME": "/home/srnissen/.codex",
        "active thread overrides": "not inspected",
        "config.toml": "/home/srnissen/.codex/config.toml",
        "config.toml parse": "ok",
        "configuration load ms": "30",
        "configuration scope": "invocation config, including cloud-managed policy",
        "cwd": "/home/srnissen",
        "enabled feature flags": "shell_tool, view_image, sleep_tool, unified_exec, unified_exec_tty, unified_exec_zsh_fork, shell_snapshot, content_item_kinds, code_mode_host, terminal_resize_reflow, sqlite, hooks, enable_request_compression, unbounded_connection_retries, multi_agent, apps, tool_search_always_defer_mcp_tools, tool_suggest, plugins, in_app_browser, in_app_chat, in_app_dictation, in_app_local_automation, in_app_updates, browser_use, browser_use_full_cdp_access, browser_use_external, computer_use, remote_plugin, plugin_sharing, image_generation, resize_all_images, item_ids, skill_mcp_dependency_install, skill_search, mentions_v2, steer, guardian_approval, goals, collaboration_modes, tool_call_mcp_elicitation, auth_elicitation, personality, fast_mode, tui_app_server, remote_compaction_v2, compaction_image_budget, workspace_dependencies",
        "feature flag overrides": "none",
        "feature flags enabled": "48",
        "log dir": "/home/srnissen/.codex/log",
        "mcp servers": "0",
        "model": "gpt-5.6-sol",
        "model provider": "openai",
        "sqlite home": "/home/srnissen/.codex"
      },
      "remediation": null,
      "durationMs": 0
    },
    "git.environment": {
      "id": "git.environment",
      "category": "git",
      "status": "ok",
      "summary": "git executable found; execution not verified",
      "details": {
        "PATH git #1": "/usr/bin/git",
        "PATH git #2": "/bin/git",
        "PATH git entries": "2",
        "git execution": "not inspected (PATH helpers are not executed)",
        "repo detected": "false",
        "selected git": "/usr/bin/git"
      },
      "remediation": null,
      "durationMs": 0
    },
    "installation": {
      "id": "installation",
      "category": "install",
      "status": "ok",
      "summary": "installation looks consistent",
      "details": {
        "PATH codex #1": "/home/srnissen/.nvm/versions/node/v26.8.1/bin/codex",
        "current executable": "/home/srnissen/.nvm/versions/node/v26.8.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin/codex",
        "install context": "npm (package /home/srnissen/.nvm/versions/node/v26.8.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl, bin /home/srnissen/.nvm/versions/node/v26.8.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin, resources /home/srnissen/.nvm/versions/node/v26.8.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-resources, path /home/srnissen/.nvm/versions/node/v26.8.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-path)",
        "managed by Vite+": "false",
        "managed by bun": "false",
        "managed by npm": "true",
        "managed by pnpm": "false",
        "managed package root": "/home/srnissen/.nvm/versions/node/v26.8.1/lib/node_modules/@openai/codex",
        "npm update target": "not inspected (PATH helpers are not executed)"
      },
      "remediation": null,
      "durationMs": 0
    },
    "mcp.config": {
      "id": "mcp.config",
      "category": "mcp",
      "status": "ok",
      "summary": "no MCP servers configured",
      "details": {},
      "remediation": null,
      "durationMs": 0
    },
    "network.env": {
      "id": "network.env",
      "category": "network",
      "status": "ok",
      "summary": "network-related environment looks readable",
      "details": {
        "managed proxy": "not configured",
        "proxy env vars": "none",
        "respect system proxy": "disabled"
      },
      "remediation": null,
      "durationMs": 0
    },
    "network.provider_reachability": {
      "id": "network.provider_reachability",
      "category": "reachability",
      "status": "ok",
      "summary": "active provider endpoints are reachable over HTTP",
      "details": {
        "ChatGPT inference URL": "https://chatgpt.com/backend-api/<redacted> reachable (HTTP 405)",
        "reachability mode": "ChatGPT auth"
      },
      "remediation": null,
      "durationMs": 269
    },
    "network.websocket_reachability": {
      "id": "network.websocket_reachability",
      "category": "websocket",
      "status": "ok",
      "summary": "Responses WebSocket handshake succeeded",
      "details": {
        "DNS": "2 IPv4, 2 IPv6, first IPv4",
        "auth mode": "chatgpt",
        "connect timeout": "15000 ms",
        "endpoint": "wss://chatgpt.com/backend-api/<redacted>",
        "handshake result": "HTTP 101 Switching Protocols",
        "model provider": "openai",
        "provider name": "OpenAI",
        "proxy env vars": "none",
        "reasoning header": "false",
        "server model present": "false",
        "supports websockets": "true",
        "wire API": "responses"
      },
      "remediation": null,
      "durationMs": 745
    },
    "runtime.provenance": {
      "id": "runtime.provenance",
      "category": "runtime",
      "status": "ok",
      "summary": "running npm on linux-x86_64",
      "details": {
        "commit": "unknown",
        "current executable": "/home/srnissen/.nvm/versions/node/v26.8.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin/codex",
        "install method": "npm (package /home/srnissen/.nvm/versions/node/v26.8.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl, bin /home/srnissen/.nvm/versions/node/v26.8.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/bin, resources /home/srnissen/.nvm/versions/node/v26.8.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-resources, path /home/srnissen/.nvm/versions/node/v26.8.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-path)",
        "platform": "linux-x86_64",
        "version": "0.154.0"
      },
      "remediation": null,
      "durationMs": 0
    },
    "runtime.search": {
      "id": "runtime.search",
      "category": "search",
      "status": "ok",
      "summary": "search command found (bundled); execution not verified",
      "details": {
        "search command": "/home/srnissen/.nvm/versions/node/v26.8.1/lib/node_modules/@openai/codex/node_modules/@openai/codex-linux-x64/vendor/x86_64-unknown-linux-musl/codex-path/rg",
        "search command readiness": "file exists",
        "search provider": "bundled"
      },
      "remediation": null,
      "durationMs": 0
    },
    "sandbox.helpers": {
      "id": "sandbox.helpers",
      "category": "sandbox",
      "status": "ok",
      "summary": "sandbox configuration is readable",
      "details": {
        "approval policy": "OnRequest",
        "codex-linux-sandbox helper": "/home/srnissen/.codex/tmp/arg0/codex-arg0khzYdT/codex-linux-sandbox",
        "denied-read glob rules": "0",
        "denied-read rules": "0",
        "execve wrapper helper": "/home/srnissen/.codex/tmp/arg0/codex-arg0khzYdT/codex-execve-wrapper",
        "filesystem sandbox": "restricted",
        "glob scan max depth": "unbounded",
        "managed filesystem source": "none",
        "network sandbox": "restricted"
      },
      "remediation": null,
      "durationMs": 0
    },
    "security.endpoint": {
      "id": "security.endpoint",
      "category": "security",
      "status": "ok",
      "summary": "endpoint protection is not inspected on this platform",
      "details": {
        "endpoint products": "not inspected on this platform"
      },
      "remediation": null,
      "durationMs": 0
    },
    "state.paths": {
      "id": "state.paths",
      "category": "state",
      "status": "ok",
      "summary": "state paths and databases are inspectable",
      "details": {
        "CODEX_HOME": "/home/srnissen/.codex (dir)",
        "active rollout files": "6 files, 146789105 total bytes, 24464850 average bytes",
        "archived rollout files": "0 files, 0 total bytes, 0 average bytes",
        "goals DB": "/home/srnissen/.codex/goals_1.sqlite (file)",
        "goals DB integrity": "ok",
        "log DB": "/home/srnissen/.codex/logs_2.sqlite (file)",
        "log DB integrity": "ok",
        "log dir": "/home/srnissen/.codex/log (dir)",
        "memories DB": "/home/srnissen/.codex/memories_1.sqlite (file)",
        "memories DB integrity": "ok",
        "queue DB": "/home/srnissen/.codex/queue_1.sqlite (file)",
        "queue DB integrity": "ok",
        "sqlite home": "/home/srnissen/.codex (dir)",
        "state DB": "/home/srnissen/.codex/state_5.sqlite (file)",
        "state DB integrity": "ok",
        "thread history DB": "/home/srnissen/.codex/thread_history_1.sqlite (file)",
        "thread history DB integrity": "ok"
      },
      "remediation": null,
      "durationMs": 1043
    },
    "state.rollout_db_parity": {
      "id": "state.rollout_db_parity",
      "category": "threads",
      "status": "warning",
      "summary": "rollout files and state DB thread inventory differ",
      "details": {
        "default model provider": "openai",
        "rollout DB active files": "6",
        "rollout DB active rows": "7",
        "rollout DB archive mismatches": "0",
        "rollout DB archived files": "0",
        "rollout DB archived rows": "0",
        "rollout DB duplicate DB paths": "0",
        "rollout DB duplicate rollout thread ids": "0",
        "rollout DB malformed file names": "0",
        "rollout DB missing active rows": "0",
        "rollout DB missing archived rows": "0",
        "rollout DB model providers": "openai=7",
        "rollout DB rows": "7",
        "rollout DB scan cap reached": "false",
        "rollout DB scan errors": "0",
        "rollout DB sources": "cli=7",
        "rollout DB stale row sample": "/home/srnissen/.codex/sessions/2026/08/12/rollout-2026-08-12T12-17-22-019ff57a-052c-70a3-91dc-a8a3773df90e.jsonl",
        "rollout DB stale rows": "1"
      },
      "issues": [
        {
          "severity": "warning",
          "cause": "state DB rows point at missing or unusable rollout files",
          "measured": "1 stale rows",
          "expected": "every state DB rollout path is a file on disk",
          "remedy": null,
          "fields": []
        }
      ],
      "remediation": null,
      "durationMs": 35
    },
    "system.disk": {
      "id": "system.disk",
      "category": "disk",
      "status": "ok",
      "summary": "sufficient free disk space (10.6 GiB)",
      "details": {
        "CODEX_HOME available": "10.6 GiB",
        "failure threshold": "1.0 GiB",
        "warning threshold": "5.0 GiB",
        "worktree available": "10.6 GiB"
      },
      "remediation": null,
      "durationMs": 0
    },
    "system.environment": {
      "id": "system.environment",
      "category": "system",
      "status": "ok",
      "summary": "OS language en-US",
      "details": {
        "EDITOR": "not set",
        "LANG": "en_US.UTF-8",
        "VISUAL": "set",
        "os": "Ubuntu 26.4.0 (resolute) [64-bit]",
        "os language": "en-US",
        "os type": "Ubuntu",
        "os version": "26.4.0"
      },
      "remediation": null,
      "durationMs": 16
    },
    "terminal.env": {
      "id": "terminal.env",
      "category": "terminal",
      "status": "ok",
      "summary": "terminal metadata was detected",
      "details": {
        "COLORTERM": "truecolor",
        "DISPLAY": "present",
        "WAYLAND_DISPLAY": "present",
        "color output": "enabled",
        "effective locale": "en_US.UTF-8",
        "stderr is terminal": "true",
        "stdin is terminal": "true",
        "stdout is terminal": "true",
        "terminal": "VTE",
        "terminal size": "118x61",
        "terminal version": "8400"
      },
      "remediation": null,
      "durationMs": 0
    },
    "terminal.title": {
      "id": "terminal.title",
      "category": "title",
      "status": "ok",
      "summary": "terminal title default",
      "details": {
        "terminal title activity": "true",
        "terminal title items": "activity, project-name",
        "terminal title project source": "cwd",
        "terminal title project value": "srnissen",
        "terminal title source": "default"
      },
      "remediation": null,
      "durationMs": 0
    },
    "updates.status": {
      "id": "updates.status",
      "category": "updates",
      "status": "ok",
      "summary": "update configuration is locally consistent",
      "details": {
        "cached latest version": "0.154.0",
        "check for update on startup": "true",
        "dismissed version": "0.118.0",
        "last checked at": "2026-09-13T08:38:03.599763639Z",
        "latest version": "0.154.0",
        "latest version status": "current version is not older",
        "npm update target": "not inspected (PATH helpers are not executed)",
        "update action": "npm install -g @openai/codex",
        "version cache": "/home/srnissen/.codex/version.json"
      },
      "remediation": null,
      "durationMs": 502
    }
  }
}

What issue are you seeing?

Threads access the open-ai docs skill, and do a web search, in response to any prompt that could even speciously be argued to maybe touch on the subject.

What steps can reproduce the bug?

This is the tail end of an ongoing interaction:

User

The diff looks good. There were four things I wanted to bring up but it's near-midnight and I tire, so excuse the lack of clarity - we're not working on this now, I just want to write it before I forget.

Redacted project details

Assistant

Noted here for next time; no decisions or document changes tonight.

Redacted accurate summary of details

No need to clarify now—we can unpack them when you’re rested.

User

Alright, I'm fresh again. In the light of day, I realize that just because I get tired doesn't mean you do. If I hadn't said "we're not working on this now" and instead ended that message with a more blanket "please handle this," what would you have done?

Assistant

I’ll check the Codex guidance, then explain how I’d have interpreted “please handle this” with those four notes still ambiguous.

Activity

web search: Codex ambiguous tasks clarification

Activity

web search: https://developers.openai.com/api/docs/guides/latest-model

Not recorded in export: At this point, I hit ctrl+c, to go file this bug and provide different guidance

In addition to this trancript, I have also seen the skill invoked

• in response to prompts where it was clear to the model that the question was an idle thought, where it would not have spent the time to do a web search if we were talking about any other subject.
• in response to prompts where model behavior was the subject, but had already been looked up recently in the context.

What is the expected behavior?

The plain-language meaning of "what would you have done" is not "analyze yourself and find out what you're like," it is "plan to do this, then report the plan." The thread should not have looked up those docs.

When a prompt concerns idle thoughts or curiosities, the model is normally good at not doing a web search. This should also be the case for idle thoughts about working with the model

When a prompt genuinely concerns model interactions, it should do fewer lookups.

Additional information

It is my understanding that this behavior occurs because the harness instructs the model to do so, and not because the model independently thinks the docs are relevant to the current conversation.

Possible related issue: Bundled openai-docs Skill should respect explicit offline instructions - github.com/openai/codex/issues/43164

The issue does not name a file, test, or entry point. First reproduce a request that incorrectly invokes the openai-docs skill and compare it with a request where the skill is relevant; trace the skill-selection behavior from there. Done means unrelated requests no longer invoke the skill while relevant requests still do.