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 espennilsen/pi --skill plan-modegit clone --depth 1 https://github.com/espennilsen/piWrote 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/espennilsen/pi/plan-mode)<a href="https://agentmods.dev/skills/espennilsen/pi/plan-mode"><img src="https://agentmods.dev/badge/skills/espennilsen/pi/plan-mode/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/espennilsen/pi/plan-mode"><img src="https://agentmods.dev/badge/skills/espennilsen/pi/plan-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00139 | $0.01940 |
| Opus 5.5 | $0.00056 | $0.00776 |
| Sonnet 5.5 | $0.00028 | $0.00388 |
| Haiku 4.5 | $0.00014 | $0.00194 |
Grade A, and why
plan-mode 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 1mo 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 — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Mode
When triggered, switch into planning mode: analyze the task, produce a structured plan, and wait for explicit user approval before writing any code or making changes.
The core philosophy: think deeply, communicate clearly, execute only when aligned.
When to Enter Plan Mode
- User explicitly requests it (
/plan, "plan this", "think first", etc.) - Task touches 3+ files or components
- Task involves architecture decisions, new patterns, or breaking changes
- Task is ambiguous and could be approached multiple ways
- Task involves infrastructure, CI/CD, database changes, or migrations
- You're unsure about the right approach
Plan Output Structure
Produce a plan with these sections. Adapt depth to task complexity — a small bug fix needs a lighter plan than a new feature.
1. Understanding (What)
Restate the task in your own words to confirm understanding. Call out any ambiguities or assumptions you're making. This catches misalignment early.
## Understanding
[Restate the goal in 2-3 sentences]
**Assumptions:**
- [List anything you're assuming that wasn't explicitly stated]
**Open questions:**
- [List anything you need clarified before proceeding]
If there are open questions that would significantly change the approach, STOP here and ask the user before continuing with the plan. Don't build a full plan on shaky assumptions.
2. Approach Options (How)
For non-trivial tasks, present 2-3 distinct approaches. For simple tasks, present one recommended approach with brief justification.
For each option include:
- Summary: One-line description
- How it works: Key implementation steps (keep high-level, not line-by-line)
- Pros: Why this approach is good
- Cons: Tradeoffs and risks
- Effort estimate: Relative complexity (small / medium / large)
End with a clear recommendation and why.
## Approach Options
### Option A: [Name]
**Summary:** [One line]
**How it works:** [3-5 bullet points, high-level]
**Pros:** [What's good about this]
**Cons:** [Tradeoffs]
**Effort:** [small / medium / large]
### Option B: [Name]
...
**Recommendation:** Option [X] because [reason tied to project context].
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.
- 1mo ago First seen · 219 lines · 139 tokens per session scan A 1e6cb2c08de0
plan-mode is a skill published in the GitHub repository espennilsen/pi (122 stars, last pushed 9d ago), licensed MIT. It adds 139 tokens to every session and 1,940 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.