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 Johnnybyzhang/post-plan --skill publish-plangit clone --depth 1 https://github.com/Johnnybyzhang/post-planWrote 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/johnnybyzhang/post-plan/publish-plan)<a href="https://agentmods.dev/skills/johnnybyzhang/post-plan/publish-plan"><img src="https://agentmods.dev/badge/skills/johnnybyzhang/post-plan/publish-plan/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/johnnybyzhang/post-plan/publish-plan"><img src="https://agentmods.dev/badge/skills/johnnybyzhang/post-plan/publish-plan.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 | $0.00086 | $0.00643 |
| Opus 5.5 | $0.00034 | $0.00257 |
| Sonnet 5.5 | $0.00017 | $0.00129 |
| Haiku 4.5 | $0.00009 | $0.00064 |
Grade A, and why
publish-plan 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 2mo 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publish Plan
Treat the online plan as the planning deliverable. Keep Codex in Default mode; the plugin hook blocks built-in Plan mode because its write restrictions prevent publishing.
Workflow
- Inspect the repository, files, and external facts needed to ground the plan. Do not make implementation changes unless the user also requests them.
- Ask only questions whose answers would materially change the plan and cannot be discovered. Otherwise state reasonable assumptions in the plan.
- Build a complete, polished HTML document beginning with
<!doctype html>. The plan itself is the visual artifact: use semantic HTML, responsive inline CSS, clear hierarchy, phased tasks, acceptance criteria, risks, and open questions when applicable. Make checklists and status legible without relying on the outer Post Plan viewer.- Keep it self-contained. Do not load external scripts, stylesheets, fonts, or application assets.
- Inline CSS is supported. Small inline scripts for presentation controls are supported inside the sandbox, but network requests and storage access are not.
- Include an accurate
<title>, accessible landmarks, visible focus styles, and mobile behavior.
- Check the draft for secrets, credentials, private keys, personal data, and internal URLs. Never publish them.
- Call the Post Plan
publish_planMCP tool only when the draft is ready. Pass:title, the complete document ashtml, a concisesummary, and an appropriatestatus.- The hook-provided Codex session UUID as
codex_session_id. If it is unavailable, readCODEX_THREAD_IDfrom the shell environment. Omit the field if neither is available. - Repository and branch metadata when known.
- Return the published HTTPS URL and the
codex://threads/...backlink. If publishing fails, return the complete plan in chat and say clearly that it is not live.
Revisions
Keep the returned planId and revision in conversation context. To change the same plan, send the complete revised HTML document with plan_id and expected_revision; do not create a second URL. Resolve a revision conflict by fetching or reconstructing the latest plan before retrying.
What ships with it
1 file 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.
- 2mo ago First seen · 37 lines · 86 tokens per session scan A b3d74a9abba0
publish-plan is a skill published in the GitHub repository Johnnybyzhang/post-plan (0 stars, last pushed 3mo ago), licensed MIT. It adds 86 tokens to every session and 643 once invoked, about $0.0003 per session on Opus 5.5. 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
prepare-cloudflare-production-deployment
Source-of-truth runbook for preparing this Vinext Cloudflare Workers SaaS template for production deployment. Use when setting up or auditing Cloudflare MCP resources, wrangler.jsonc bindings, Worker secrets, Turnstile, Email Sending, GitHub Actions secrets/variables, or GitHub CLI deployment wiring for this…
moemail
Use when an AI agent needs a temporary/disposable email address — for receiving verification emails, testing email integrations, or any task requiring a temporary inbox via the moemail CLI.
obsidian-sync
Set up and verify free Obsidian sync (Remotely Save plugin → Davflare WebDAV). Use when a user asks to sync an Obsidian vault to their Davflare drive.
hello-site
Reproduce a Davflare static site with existing MCP tools only (publishsite / imageupload). Use when onboarding or demoing “chat → site”.
review-stack
Stack review of one or more third-party tools (OXC, TanStack, Vite, cf, Sentry, pnpm, Claude Code...) against current official best practices, or of what a dependency bump brings (bumped): one parallel subagent per tool, verified findings, one consolidated plan in chat. USE WHEN: user runs /review-stack or explicitly…
pnpm
Fast, disk-efficient package manager for this pnpm + Turborepo monorepo. pnpm owns the dependency graph, lockfile, and supply-chain policy; Turborepo owns task orchestration (build, lint, dev, --affected).