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 skills/anhnguyen0905/codex-mcp/parallel-executionnpx skills add anhnguyen0905/codex-mcp --skill parallel-executiongit clone --depth 1 https://github.com/anhnguyen0905/codex-mcpWrote 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/skills/anhnguyen0905/codex-mcp/parallel-execution)<a href="https://agentmods.dev/skills/anhnguyen0905/codex-mcp/parallel-execution"><img src="https://agentmods.dev/badge/skills/anhnguyen0905/codex-mcp/parallel-execution.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 | $0.00111 | $0.03037 |
| Opus 5 | $0.00056 | $0.01519 |
| Sonnet 5 | $0.00022 | $0.00607 |
| Haiku 4.5 | $0.00011 | $0.00304 |
Grade A, and why
parallel-execution 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 yesterday.
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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Parallel Execution (default when wave width > 1)
codex-mcp serializes runs per cwd (to prevent file/git races) but runs different cwds in
parallel. So real parallelism = one git worktree per concurrent task, each driven by its own
Claude subagent calling codex_execute into that worktree.
Control-file ownership
The coordinator is the SOLE writer for every .codex-flow/* file, including TASKS.md, PLAN.md,
STATE.md, REQUIREMENTS.md, report directories, IMPROVEMENTS.md, and notes. Worktree subagents treat
those durable control-file copies as read-only inputs. They may regenerate derived context slices
inside their own worktree copies only; every durable update flows through the structured handoff
to the coordinator.
Default-on policy
- Always run the wave tool below during Phase 4. When it reports width > 1, use parallel mode by default if the project is a git repo, its tracked baseline is clean, and the user has not opted out.
- Proceed without asking for waves of ≤3 concurrent tasks. Show the user the wave plan, then start the wave.
- When a wave exceeds 3 concurrent tasks, ask whether to run at that width or lower the cap before spawning; parallel execution burns N× simultaneous quota.
- Stay sequential when the tool reports "fully sequential", the user opted out, the project is not a git repo, or the tracked baseline cannot be made clean.
Step 1 — Compute waves
node "${CLAUDE_PLUGIN_ROOT}/scripts/task-waves.mjs" .codex-flow/TASKS.md
A wave is a set of tasks that can run at once: every task's dependencies are satisfied by
earlier waves, and no two tasks in the wave touch the same file (Files: field). Tasks with no
declared files run alone (unknown blast radius). The tool prints each wave and its width; a wave
of width 1 just runs like normal Phase 4.
Wave quality is only as good as the backlog metadata: accurate per-task Files: sets (from PLAN.md's
Component → files map) and fixed Contracts are what make concurrent tasks genuinely
independent. If tasks were sliced with vague file lists, fix the backlog before parallelizing —
don't parallelize on guesses.
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.
- yesterday Changed · +8 lines e929a6559abc
- 5d ago First seen · 171 lines · 111 tokens per session scan A 7eb67349174a
parallel-execution is a skill published in the GitHub repository anhnguyen0905/codex-mcp (3 stars, last pushed 2d ago), licensed MIT. It adds 111 tokens to every session and 3,037 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…