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 skills/ai-swiss/base/plannpx skills add ai-swiss/base --skill plangit clone --depth 1 https://github.com/ai-swiss/baseWrote 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/ai-swiss/base/plan)<a href="https://agentmods.dev/skills/ai-swiss/base/plan"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/plan.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 | $0.00035 | $0.00529 |
| Opus 5 | $0.00017 | $0.00264 |
| Sonnet 5 | $0.00007 | $0.00106 |
| Haiku 4.5 | $0.00003 | $0.00053 |
Grade A, and why
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 3d 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.
What it actually says
Plan a change
A plan turns intent into something a junior or a context-free agent can follow
without inventing. The doctrine lives in skills/competences/code-planning/SKILL.md; load it and
apply it. The shape lives in templates/plan.md.
Steps
- Ground first. Run
understand-state(or readspecs/and the matrix) so the plan rests on what exists, not on memory. - Ask only design-changing questions. Three at most, each with concrete options; if visual, an ASCII mock-up per option. Record the answers in the plan's Origin section. If the user proposes something better, take it.
- Write the plan to
.plans/YYYY-MM-DD_subject.mdfromtemplates/plan.md: origin, non-negotiable rules + exact verification commands, engineering doctrine (named principles anchored in this ticket), the slice table, detailed vertical slices, known traps, the self-review grid, the definition of done. - Keep slices vertical, green, irreversible. Each one crosses all layers and ships observable behaviour; each ends with every gate green; each kills the code it replaces in the same slice.
- Hand off to
implement, slice by slice.
What you never do
- Write truth into the plan: the plan is disposable, the code and
specs/are the source. - Leave a fuzzy task (no end test means not ready) or plan speculative generality for two cases.
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.
- 3d ago First seen · 50 lines · 35 tokens per session scan A 532065ae6fe1
plan is a skill published in the GitHub repository ai-swiss/base (42 stars, last pushed 20d ago), licensed Apache-2.0. It adds 35 tokens to every session and 529 once invoked, about $0.0002 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
pr-to-video
Turn a GitHub pull request (a PR URL, owner/repo#N, or 'this PR' in a checked-out repo) into a code-change explainer video — changelog, feature reveal, fix, or refactor walkthrough built from the diff, commits, and files: the input is a code change, not a website. Not a product promo (/product-launch-video) or a no-PR…
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…
implementation-final-review
Perform the repository's risk-tiered independent final review before implementation completion. Use only when explicitly invoked or when repository instructions require it after behavior-impacting implementation work; audit the complete task diff, supported contracts, lifecycle and security boundaries, complexity, and…
hyperframes-core
The HyperFrames composition contract — build one renderable project. Use for composition structure, the data- timing attributes, class="clip", tracks, sub-compositions, variables, framework-owned media playback, deterministic-render rules, and validation. Also covers Tailwind projects and the STORYBOARD.md / SCRIPT.md…
technical-writing
Write, edit, review, or audit user-facing documentation for the eve repository. Use for changes under docs/, documentation tied to eve APIs or CLI behavior, docs work based on Slack or support feedback, and requests to make eve docs clearer, more natural, or less AI-patterned while verifying claims against current…