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 randommonicle/claude-skills --skill plan-firstgit clone --depth 1 https://github.com/randommonicle/claude-skillsWrote 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/randommonicle/claude-skills/plan-first)<a href="https://agentmods.dev/skills/randommonicle/claude-skills/plan-first"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/plan-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/randommonicle/claude-skills/plan-first"><img src="https://agentmods.dev/badge/skills/randommonicle/claude-skills/plan-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 | $0.00067 | $0.00898 |
| Opus 5 | $0.00034 | $0.00449 |
| Sonnet 5 | $0.00013 | $0.00180 |
| Haiku 4.5 | $0.00007 | $0.00090 |
Grade A, and why
plan-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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan before code
On any non-trivial commit, state the plan explicitly before writing any code. Wait for the user's confirmation before touching files.
When this applies
This skill fires on:
- New features
- Schema-touching changes (migrations, type definitions)
- Multi-file refactors
- Any work that creates new files or modifies more than two existing files
- Work where the right shape is not yet obvious from the user's request
This skill does not fire on:
- One-line bug fixes
- Doc typo corrections
- Trivial config tweaks where the change is fully specified by the user's request
If unsure whether a commit qualifies, treat it as non-trivial and produce the plan. The cost of a plan-first gate on a small commit is one round-trip; the cost of skipping it on a large one is rework.
What the plan must contain
- New files. Every file that will be created, with its purpose in one line.
- Modified files. Every existing file that will be touched, with what changes.
- Out-of-scope items. Anything the user might reasonably expect to be in this commit but is deliberately deferred. Each deferred item should be flagged per the flag-deferred-items skill (plant a grep-able anchor at the future landing point).
- Test list. Concrete test names with one-line descriptions per test. Not categories; named tests.
- Decisions or rules to record. Any design call that should land in a DECISIONS file or equivalent. Cite the project's convention.
How to apply
After producing the plan, stop. Wait for explicit go-ahead before writing code.
If the project has additional plan-first requirements (migration verification queries, competitor-parity audits, UX rule enumeration, etc.), the project-level CLAUDE.md or project memory will name them. Read those before producing the plan so the plan contains everything the project requires.
If the user proceeds without explicit confirmation language but with substantive feedback on the plan, treat that feedback as the go-ahead conditional on the changes they named.
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 · 65 lines · 67 tokens per session scan A 39c9bb1222db
plan-first is a skill published in the GitHub repository randommonicle/claude-skills (23 stars, last pushed 2d ago), licensed Apache-2.0. It adds 67 tokens to every session and 898 once invoked, about $0.0003 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…