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 skills add anhnguyen0905/codex-mcp --skill plan-research-firstgit 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/plan-research-first)<a href="https://agentmods.dev/skills/anhnguyen0905/codex-mcp/plan-research-first"><img src="https://agentmods.dev/badge/skills/anhnguyen0905/codex-mcp/plan-research-first/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/anhnguyen0905/codex-mcp/plan-research-first"><img src="https://agentmods.dev/badge/skills/anhnguyen0905/codex-mcp/plan-research-first.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00034 | $0.00448 |
| Opus 5 | $0.00017 | $0.00224 |
| Sonnet 5 | $0.00007 | $0.00090 |
| Haiku 4.5 | $0.00003 | $0.00045 |
Grade A, and why
plan-research-first 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 9d 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.
What it actually says
Research First
Never design from a blank page. Cheapest code is code you don't write; second cheapest follows a pattern that already works.
Order of research (stop at the first sufficient hit)
- This codebase — Is there an existing feature that does 80% of this? Follow its structure, naming, error handling, and test style exactly. Grep for similar routes/components/services before inventing new ones.
- Installed dependencies — Does a library already in package.json/pyproject/go.mod solve it? Prefer using what's installed over adding anything.
- Package registries (npm/PyPI/crates/Go modules) — For utility problems (dates, validation, parsing, retries), a battle-tested library beats hand-rolled code. Check: weekly downloads, last release date, open issues, license.
- Reference implementations —
gh search code/gh search reposand official docs for how others solved the same problem; port the approach, not the code.
What to record in PLAN.md
For each significant choice: what was found, what was chosen, and why the alternatives lost — one line each. This stops the "why didn't we just use X?" review round. Record any new dependency under PLAN.md's Risk & blast radius (with license + maintenance status), and reflect a reused in-repo pattern in the Contracts / Component → files sections so the backlog slices along it.
Guardrails
- New dependency = a decision the user should see in the plan, with license and maintenance status noted.
- Do NOT hand-roll: crypto, auth/session logic, date/timezone math, parsers for standard formats (CSV/YAML/JWT), retry/backoff. Libraries exist and get these right.
- Do NOT add a dependency for something under ~20 lines of obvious code (left-pad rule).
- Version-check assumptions: confirm API shapes against the installed version's docs, not memory.
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.
- 9d ago First seen · 27 lines · 34 tokens per session scan A 65c9df74000c
plan-research-first is a skill published in the GitHub repository anhnguyen0905/codex-mcp (3 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 448 once invoked, about $0.0002 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…