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 nicograef/handbook --skill plangit clone --depth 1 https://github.com/nicograef/handbookWrote 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/nicograef/handbook/plan)<a href="https://agentmods.dev/skills/nicograef/handbook/plan"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/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/nicograef/handbook/plan"><img src="https://agentmods.dev/badge/skills/nicograef/handbook/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 | $0.00072 | $0.00893 |
| Opus 5.5 | $0.00029 | $0.00357 |
| Sonnet 5.5 | $0.00014 | $0.00179 |
| Haiku 4.5 | $0.00007 | $0.00089 |
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 12d 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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan
Arguments: $ARGUMENTS. The output is a file, never code. /nico:plan <task or PRD path> writes docs/plans/plan-<slug>.md; /nico:plan prd <problem> writes docs/prds/prd-<name>.md.
What implement-plan relies on
- The plan keeps the skeleton. implement-plan and the
plan-run-guard.shStop hook parse## Phase,**Depends on**and- [ ]lines. - Paths go in each phase's Context and What to build. The concurrency test compares them pairwise.
- Phases meant to run in parallel touch disjoint files. Choke files (indexes, lockfiles, migrations) stay in one phase.
- A refactor that fans across the tree runs expand, migrate, contract. Expand adds the new form beside the old. Migrate phases are batched per package, parallel on disjoint files. Contract removes the old form and depends on every migrate phase.
- Each criterion is verified by one targeted command. An existing gate, test or command output comes first; a new test only where nothing covers the behaviour. The full gate runs once per phase.
- Reference code as
path — symbol(), not line numbers; lines drift while phases land.
Plan mode
- Read the input in full: the PRD, or the task and the code it touches.
- Ask only what code, PRD and conventions leave open, in at most three rounds. Zero questions is normal.
- Fix the durable decisions in the header: routes, schema, models, auth, third-party boundaries.
- Slice into tracer-bullet phases, each a thin path through every layer and demoable alone. Pick the granularity yourself.
- Self-review: fix placeholders such as TBD or "similar to phase N". Flag names used in one phase only. Propose KISS and YAGNI cuts.
- Spawn a fresh-context
opusplan critic on the file. Apply its findings and your cuts; route only forks with no clear winner through the decide skill.
PRD mode
- Split a request bundling independently shippable features into separate PRDs.
- Check the user's assertions against the code, then clarify in at most three rounds.
- Weigh two or three approaches by effort, risk and reversibility. Record the pick and why.
- Write the sections of the PRD skeleton in one pass.
- New domain terms go into the repo's glossary, else
docs/UBIQUITOUS_LANGUAGE.md: term, one-sentence definition, aliases to avoid. - Self-review as in plan mode.
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.
- 12d ago Changed · +1 lines 7a9365f5ba12
- 16d ago Changed · +2 lines 9af8447baf20
- 18d ago Changed · -26 lines 199b7fead0b5
- 28d ago Changed e6691c3b21e6
- 1mo ago Changed · +6 lines c0b4ba2e13ba
- 1mo ago Changed 72a09c499898
- 1mo ago Changed · +1 lines 85b6c0f39eed
- 1mo ago Changed 1cb59c4c20b2
- 1mo ago Changed · +2 lines 4d3656059318
- 1mo ago First seen · 89 lines · 72 tokens per session scan A 183a79b3eb0e
plan is a skill published in the GitHub repository nicograef/handbook (2 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 893 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 2026-09-14.
plan compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| plannicograef/handbook | Skill | 2 | 2d ago | MIT | A | 72 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |