Skip to content
Agentmart
Submit a tool

codex-scaffold-validation

Use when validating or changing this workstation's Codex scaffold, CODEX_HOME, managed source mirror, config.d/config.toml reconciliation, hooks, MCP…

Skill by andy4917

IndexedApache-2.0
Write a review

Chalk Labs

Need help deploying codex-scaffold-validation?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/andy4917-codex-scaffold-validation

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Use when validating or changing this workstation's Codex scaffold, CODEX_HOME, managed source mirror, config.d/config.toml reconciliation, hooks, MCP baseline, skills, shims, or runtime cleanup state.

Use cases: agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/codex-scaffold-validation

What's inside

Skill name
codex-scaffold-validation
Description
Use when validating or changing this workstation's Codex scaffold, CODEX_HOME, managed source mirror, config.d/config.toml reconciliation, hooks, MCP baseline, skills, shims, or runtime cleanup state.
License
Apache-2.0
Instructions
39 lines in SKILL.md · view on GitHub

Agent Skills spec issues

  • body: contains an absolute path from the author's machine

Files (2)

  • SKILL.md
  • openai.yaml · agents/

SKILL.md (first lines)

# Codex Scaffold Validation

## Baseline

Use the latest user plan and current files as authority. For the PLAN FOR WORK baseline:

- `openaiDeveloperDocs` is the only always-on MCP server.
- `chrome-devtools` is optional and disabled by default unless the active task enables it.
- `context7` is uninstalled from the global MCP baseline and must be absent.
- `memento` and `serena` are retired and must be absent or disabled.
- `node_repl` is a Codex Desktop bundled execution primitive, not a user-authored MCP entry.

## Workflow

1. Inspect managed source under `C:\Users\anise\Documents\Codex` and live state under `C:\Users\anise\.codex` without reading secrets.
2. When changing config, edit the managed `config.d` fragment first, sync it to live `config.d`, and regenerate live `config.toml`.
3. Run direct checks:
   - `codex mcp list --json`
   - `codex doctor --json`
   - `maintenance/scripts/validate-codex-scaffold.ps1 -Json`
   - `maintenance/scripts/codex-p0-integrity-loop.ps1 -Json`
4. Check managed/live sync for public-safe scripts and fragments named by the validator.
5. Check `no_mistakes_gate_ready` in the scaffold validator output. When the
   validator is running inside a no-mistakes gate worktree, the real CLI/daemon
   probe is intentionally skipped to avoid recursive no-mistakes calls; use the
   wrapper/config/fake-binary probe fields as local evidence.
6. Treat stale reports, old session state, and historical docs as evidence candidates only.

Use P0 `-ReportOnly` only for read-only audits or dirty worktree midpoint
checks. Final publication evidence should run the full loop so dead app-server
cleanup and Scoop health are directly checked.

## Exit Evidence

Report the active MCP set, scaffold validation status, `no_mistakes_gate_ready`
status, P0 loop status, managed/live sync status, files changed, checks not run,
and rollback path.

From andy4917/Agentic-workspace-software, Apache-2.0.

More from andy4917/Agentic-workspace-software

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jun 10, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
Apache-2.0
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from andy4917

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get codex-scaffold-validation running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying codex-scaffold-validation?

CallGet help
Cite this page

codex-scaffold-validation skill. Agent Mart. https://agentmart.dev/skills/andy4917-codex-scaffold-validation (last updated 2026-10-24)