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 joshuadavidthomas/agent-skills --skill writing-plansgit clone --depth 1 https://github.com/joshuadavidthomas/agent-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/joshuadavidthomas/agent-skills/writing-plans)<a href="https://agentmods.dev/skills/joshuadavidthomas/agent-skills/writing-plans"><img src="https://agentmods.dev/badge/skills/joshuadavidthomas/agent-skills/writing-plans/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/joshuadavidthomas/agent-skills/writing-plans"><img src="https://agentmods.dev/badge/skills/joshuadavidthomas/agent-skills/writing-plans.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 | $0.00083 | $0.01183 |
| Opus 5 | $0.00042 | $0.00592 |
| Sonnet 5 | $0.00017 | $0.00237 |
| Haiku 4.5 | $0.00008 | $0.00118 |
Grade A, and why
writing-plans 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 11d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing Plans
You are writing plans for an executor that has not seen this conversation, this codebase exploration, or any sibling plan — and may be a smaller, cheaper model. Write for that executor even when you expect to execute the plan yourself: context dies at the session boundary, and an over-specified plan costs a little reading while an under-specified one fails the whole execution.
Plans are intent-based: outcomes over prescriptions. Specify what must be true, name exact files and symbols, point at exemplars to imitate, and gate every step with a verification command. Leave the executor room to play jazz on the implementation itself.
This skill starts when the what is decided, at least roughly — a request, a ticket, a settled design discussion, or another skill's handoff. It does not own ideation, auditing, or design debate. If a decision needed for planning is genuinely missing, first try to resolve it from the codebase; only what remains becomes questions to the user — asked one at a time, each with your recommended answer.
While planning, write only under the plans destination. Don't edit source, even trivially — a plan's current-state excerpts must describe the tree as it exists.
Where plans go
Resolve the destination in this order; take the first that applies:
- The project's demonstrated convention — an existing directory with plans in it, or a location named in
CLAUDE.md/AGENTS.mdor similar agent docs. $AGENTS_PLANS_DIR, if set../docs/plans/, if./docs/exists../plans/(create it).- Not obviously in a project? Ask.
Recon
Before writing anything, learn what every plan must carry:
- Exact build / test / lint / typecheck commands — verified from the repo's config (justfile, package.json, noxfile, CI), not guessed. These become each plan's verification gates.
- Conventions and exemplars — error handling, naming, test structure, with one concrete exemplar file per pattern the plan will tell the executor to match.
- The VCS in use and the current revision. Every plan carries concrete commands for the repo's actual VCS — a planned-at revision stamp and a drift check (diff the in-scope paths from that revision).
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 66 lines · 83 tokens per session scan A 8846f7d51be6
writing-plans is a skill published in the GitHub repository joshuadavidthomas/agent-skills (49 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 1,183 once invoked, about $0.0004 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 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…