Borrowing it
Nothing to install: this file belongs to ai-swiss/base. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/ai-swiss/base/main/.ai/agents/base-contributor/skills/processes/plan/SKILL.mdgit 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/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/ai-swiss/base/plan"><img src="https://agentmods.dev/badge/skills/ai-swiss/base/plan.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 | $0.00035 | $0.00529 |
| Opus 5.5 | $0.00014 | $0.00212 |
| Sonnet 5.5 | $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 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.
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.
- 2mo ago First seen · 50 lines · 35 tokens per session scan A 532065ae6fe1
plan is a skill published in the GitHub repository ai-swiss/base (65 stars, last pushed 8d ago), licensed Apache-2.0. It adds 35 tokens to every session and 529 once invoked, about $0.0001 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.
plan compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| planai-swiss/base | Skill | 65 | 8d ago | Apache-2.0 | A | 35 | Claude Code |
| complianceericrisco/rsc-harness | Skill | 503 | 2d ago | MIT | A | 96 | Claude Code, Codex |
| wallet-cliBofAI/skills | Skill | 164 | 4d ago | MIT | A | 92 | Codex |
| vaultjoelhooks/joelclaw | Skill | 65 | yesterday | none | A | 82 | Claude Code |
| feishuHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 33 | Claude Code, Codex |
| interviewHmbown/CodeWhale | Skill | 41k | 5d ago | MIT | A | 40 | Claude Code, Codex |
| atmos-validationcloudposse/atmos | Skill | 1.4k | yesterday | Apache-2.0 | A | 31 | Claude Code |