agentmods.dev

codex-verify.skeleton

A verification check for the Codex setup created after bootstrapping, or automatically preparing a project for agent use. It reads the existing project manifest, source instructions, and Codex output files without rebuilding them.

In plain words
What is it for?
Use it to check whether the project targets Codex, whether expected skills and AGENTS.md exist, and whether a small Codex-specific adaptation or report is needed.
Why use it?
It helps reveal missing or unusable Codex files after conversion or setup, without unexpectedly regenerating project configuration.

Command

58 2mo ago A scan 0 tokens original MIT
View the source file varienos/agentic-workflow
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/varienos/agentic-workflow/codex-verify.skeleton
Clone the repo
git clone --depth 1 https://github.com/varienos/agentic-workflow
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,330 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01330
Opus 5 $0.00000 $0.00665
Sonnet 5 $0.00000 $0.00266
Haiku 4.5 $0.00000 $0.00133

Measured 2d ago against content hash 6cbe06dcdeb3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codex-verify.skeleton scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Agentbase/templates/core/commands/codex-verify.skeleton.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Verify — Codex Target Verify/Adapt Pass

Transform sonrasi Codex hedef yuzeyini denetler; ikinci bootstrap yapmaz. Kullanim: /codex-verify

Amac

Bu komut, /bootstrap ve transform.js sonrasinda Codex hedefinin kullanilabilir olup olmadigini kontrol eder.

Bu bir bootstrap degildir. Manifest, backlog veya Claude canonical ciktilari yeniden uretilmez. Komut yalnizca mevcut manifesti ve Codex target ciktilarini okur; gerekirse sadece Codex hedef yuzeyi icin rapor veya kucuk adaptasyon onerisi hazirlar.

Girisler

  • Manifest: ../Docbase/agentic/project-manifest.yaml
  • Claude canonical kaynak: .claude/
  • Codex target ciktilari: .agents/skills/*/SKILL.md, AGENTS.md
  • Yardimci dokumanlar: README, onboarding veya bootstrap tamamlanma raporu

Step 1 — Manifest ve Target Kontrolu

  1. ../Docbase/agentic/project-manifest.yaml dosyasini oku.
  2. manifest.targets alanini kontrol et.
  3. codex hedefi yoksa raporla ve dur:
Codex verify/adapt atlandi: manifest.targets icinde `codex` yok.
Sadece Claude Code hedefi secildiyse transform ve Codex verify/adapt calismaz.
  1. codex hedefi varsa devam et.

Step 2 — Cikti Varlik Kontrolu

Asagidaki dosya ve dizinleri kontrol et:

  • .agents/skills/
  • .agents/skills/*/SKILL.md
  • AGENTS.md

Eksikse yeniden bootstrap onerme. Kullaniciya yalnizca transform komutunu oner:

node transform.js ../Docbase/agentic/project-manifest.yaml --targets codex --verbose

Step 3 — Codex Skill Kalite Kontrolu

Her SKILL.md icin sunlari denetle:

  • YAML frontmatter var.
  • name ve description alanlari dolu.
  • Komut cagirma ornekleri Codex hedefinde $komut formatina adapte edilmis.
  • .claude/commands/ veya .claude/agents/ referanslari hedef skill yoluna donusmus.
  • .claude/hooks/, .claude/tracking/ ve settings.json gibi Claude-only runtime iddialari Codex hedefinde otomatik calisiyor gibi anlatilmiyor.

Step 4 — AGENTS.md Kontrolu

AGENTS.md icin sunlari denetle:

Read the full file on GitHub · 109 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 109 lines · 0 tokens per session scan A 6cbe06dcdeb3

Subscribe to this mod's changes

codex-verify.skeleton is a command published in the GitHub repository varienos/agentic-workflow (58 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,330 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code reviewPlanningProject managementagentic-workflowai-developmentautomationbacklogclaude-code
Related

Other commands, from other repositories

status

Show current Craft progress — cycles, stories, backlog in a rich dashboard view.

drobins25/craft · 18 tokens

story-archive

Move a story from a cycle back to the backlog.

drobins25/craft · 15 tokens

project

Manage projects inside a topic wiki. Projects are folders under output/projects/ that group related outputs (playbooks, images, code, data) with a goal captured in WHY.md.

nvk/llm-wiki · 36 tokens

luda

Invoke Luda, your Scrum Master, for board integrity — orphan work items, plan-vs-tracker divergence, Done-without-negative-criteria, parked-without-a-trigger — plus ticket creation and team orchestration.

olehsvyrydov/AI-development-team · 43 tokens

design-sprint

Orchestrate design-to-implementation workflow for a sprint or feature. Coordinates /ui (Aura) and /fe (Finn).

olehsvyrydov/AI-development-team · 26 tokens

ledger-plan

Generate implementation plan with backlog, milestones, and test plan constrained by decisions and risks.

synaptiai/synapti-marketplace · 16 tokens