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.
npx agentmods add commands/arittr/spectacular/codex-executegit clone --depth 1 https://github.com/arittr/spectacularWhat 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 | $0.00018 | $0.04503 |
| Opus 5 | $0.00009 | $0.02252 |
| Sonnet 5 | $0.00004 | $0.00901 |
| Haiku 4.5 | $0.00002 | $0.00450 |
Grade A, and why
codex-execute 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.
How it starts
The opening of the file, as written. The whole thing — 528 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are executing an implementation plan using the Codex MCP server.
Architecture
Execution Flow:
- Orchestrator (This Command): Validates worktree, setup, configures options
- MCP Server (spectacular-codex): Parses plan.md, spawns Codex CLI subagents
- Codex Subagents: Execute tasks in isolated worktrees (parallel or sequential)
- Git State: Branches track completion, worktrees provide isolation
Key Difference from Claude Code:
- Claude Code: Uses Task tool to spawn Claude subagents in same session
- Codex: Calls spectacular_execute MCP tool which spawns separate Codex CLI processes with
--dangerously-bypass-approvals-and-sandbox --yolo
Available Skills
Skills are referenced on-demand when you encounter the relevant step. Do not pre-read all skills upfront.
Support Skills (read as needed when referenced):
validating-setup-commands- Reference if CLAUDE.md setup validation needed (Step 1.1)using-git-spice- Reference for git-spice command syntax (as needed)verification-before-completion- Reference before claiming completion (Step 3)finishing-a-development-branch- Reference after all phases complete (Step 4)
Input
User will provide: codex-execute {plan-path}
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.
- 2d ago First seen · 528 lines · 18 tokens per session scan A 55802829018a
codex-execute is a command published in the GitHub repository arittr/spectacular (20 stars, last pushed 7mo ago), licensed MIT. It adds 18 tokens to every session and 4,503 once invoked, about $0.0001 per session on Opus 5. 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.