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 instructions/yosefhayim/planpage/agents-mdgit clone --depth 1 https://github.com/YosefHayim/planpageWrote 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/instructions/yosefhayim/planpage/agents-md)<a href="https://agentmods.dev/instructions/yosefhayim/planpage/agents-md"><img src="https://agentmods.dev/badge/instructions/yosefhayim/planpage/agents-md.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 5.1 | $0.02276 | $0.02276 |
| Opus 5 | $0.01138 | $0.01138 |
| Sonnet 5 | $0.00455 | $0.00455 |
| Haiku 4.5 | $0.00228 | $0.00228 |
Grade A, and why
planpage AGENTS.md 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 6d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Single source of truth for working in planpage. CLAUDE.md / GEMINI.md point here.
What this is
planpage — a reusable, open-source kit that renders a skill's plan / gate / report as a beautiful, self-contained local HTML page. Reader-first: the design center is the developer reading the plan. Authored as Preact components → static HTML (render(<Template {...data} />) → string); a static render is the floor, interactivity is opt-in islands (the serve post-back · the gallery filter). Clear of mcp-ui / MCP Apps (the protocol/host lane). Published unscoped as planpage — one name for the package, the CLI bin, and the import (ADR 0013). Seeded by extracting the planpage spike from dufflebag, which becomes a thin consumer.
Repo layout
| Path | Purpose |
|---|---|
src/components/ |
shared primitives (flat), grouped by role — layout (Shell · SectionCard · TreePanel · Accordion · Carousel) · notes (Callout · RiskList) · sequence (StatusChip · Steps · Timeline) · brainstorm (PickBlock · OptionCompare · QuestionCard) · teach (QuizCard · Flashcard) · metrics (PlanSummary · Scorecard) · code (DiffBlock · CodeBlock · AnnotatedCode · CodeExplorer · Terminal) · diagram (Flow) · action (FeedbackSidebar · SubmitBar) |
src/templates/<Name>/ |
pages (folder-per-template: component + test + README) — BeforeAfter, CodeStylePlan, PlanBrief (flagship agent-plan page), QuestionPoll (preference poll), Quiz (graded teach/coach quiz), Flashcards (flip-card learn deck), AuditReport (scored audit), Library (auto-captured gallery); registry in templates/index.tsx |
src/gallery/ |
the living collection — registry (SSOT) · capture (pure diff) · sync test; powers Library + planpage capture |
src/render/ |
pure engine — render(), raw(), codeMark (the data-hl marker every code component emits), clientScript/ (one island module each: theme · post-back · gallery filter · poll · quiz · explorer · carousel). Shell (in components) owns the Theme type + the animated sun/moon toggle |
src/highlight/ |
the highlight pass — an async edge transform (highlight · renderHighlighted) that swaps data-hl markers for Shiki's VSCode dual-theme spans. Not part of the pure render (ADR 0015) |
src/server/ |
opt-in post-back — serve (ephemeral port, never-hang), Decision |
src/cli/ |
dual-mode CLI (commander) — render / serve / new / library / capture / init; bare TTY → menu (clack); shared io (open/writeTemp); init/ is one writer per agent |
skills/planpage/ |
agent skill SSOT (SKILL.md + COMPONENTS.md) — how other agents use the kit; init scaffolds thinner per-agent on-ramps |
src/contracts/ |
shared types — Decision |
src/index.ts |
public API barrel |
docs/adr/current/ |
decisions (why) |
*.test.tsx (co-located) |
vitest, beside source |
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.
- 6d ago First seen · 95 lines · 2,276 tokens per session scan A e504be36a1c7
planpage AGENTS.md is an instructions file published in the GitHub repository YosefHayim/planpage (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,276 tokens to every session, about $0.0114 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 instructions, from other repositories
fieldtheory-cli CLAUDE.md
Instructions for afar1/fieldtheory-cli, covering claude.md, commands, architecture, key files and data flow.
browser-bridge AGENTS.md
AGENTS.md instructions for koltyakov/browser-bridge, covering project guide, data flow, package map, where to find things and method dispatch (extension side).
hermes-agent-harness-plus CLAUDE.md
Claude Code instructions for phenomenoner/hermes-agent-harness-plus, covering claude.md, what this repo is, before touching readme, docs/, or the website, commands and deployment.
wrench AGENTS.md
AGENTS.md instructions for hraness/wrench, a project described as: Open-source CLI and TypeScript SDK for precise web capabilities for AI agents: page capture, verified media archives, encrypted reads, and typed provider operations.
hermes-agent-harness-plus AGENTS.md
AGENTS.md instructions for phenomenoner/hermes-agent-harness-plus: Working in this repo with an AI agent? Start here.
web-cap AGENTS.md
Instructions for edgestorage/web-cap, covering agent notes and beta release flow.