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.
git clone --depth 1 https://github.com/marcusgoll/Spec-FlowWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/marcusgoll/spec-flow/codex_compatibility)<a href="https://agentmods.dev/commands/marcusgoll/spec-flow/codex_compatibility"><img src="https://agentmods.dev/badge/commands/marcusgoll/spec-flow/codex_compatibility.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00490 |
| Opus 5 | $0.00000 | $0.00245 |
| Sonnet 5 | $0.00000 | $0.00098 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
CODEX_COMPATIBILITY 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Compatibility Guide (for .codex/commands/)
Codex CLI cannot invoke Claude-specific tools (Task, SlashCommand, AskUserQuestion, Skill, TodoWrite) or spawn subagents. Use this shim to keep the same behaviors with Codex-only capabilities (shell + file edits).
Supported tools in this repo: shell (bash/pwsh/python), file read/write, and the skills index loader (node .codex/skills/test-skill-call.js).
Tool Substitutions
SlashCommand(/phase)→ Run the underlying script shown in the command (typicallypython .spec-flow/scripts/spec-cli.py <phase> ...), or execute the bash/PowerShell block verbatim.Task/ subagents → Execute the described steps yourself, sequentially. Use the routing logic as guidance, but do not call Task; stay in the same conversation and run the shell steps directly.AskUserQuestion→ Ask the user inline in chat. Keep the same batching/option structure manually.Skill(name)→ Load the skill content withnode .codex/skills/test-skill-call.js <name>and follow its SOP manually (no Skill tool).TodoWrite→ Edittasks.md/state.yamldirectly withapply_patch, keeping atomic updates.
When a command says…
- “Launch X agents in parallel” → Run those steps one-by-one; note the intended parallelism.
- “Call /spec /plan /tasks …” → Invoke the scripts already embedded in the command (bash/ps) instead of slash commands.
- “Use question bank via AskUserQuestion” → Manually present the same options/questions in chat, then proceed with the user’s answers.
Quick workflow shims
- Feature phases:
python .spec-flow/scripts/spec-cli.py spec|clarify|plan|tasks|implement|optimize|finalize "$ARGS" - Deployment: Follow the bash/ps blocks inside
deployment/*.md; they are executable as-is. - Skills:
node .codex/skills/test-skill-call.js --listthennode .codex/skills/test-skill-call.js <skill>
Apply these substitutions before executing any command text in this directory. This preserves intent without relying on Claude-only tools.
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.
- 3d ago First seen · 28 lines · 0 tokens per session scan A a3d404f01fa2
CODEX_COMPATIBILITY is a command published in the GitHub repository marcusgoll/Spec-Flow (92 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 490 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 2026-09-03.
Other commands, from other repositories
opsx-apply
Implement tasks from an OpenSpec change (Experimental).
OPSX: Apply
Implement tasks from an OpenSpec change (Experimental).
OPSX: Bulk Archive
Archive multiple completed changes at once.
adopt-roadmap.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
todo.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.
update-check.template
This prompt was authored for Claude-style slash workflows. In Codex runtime, adapt tool calls as follows.