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 maxedapps/agent-skills --skill create-plangit clone --depth 1 https://github.com/maxedapps/agent-skillsWrote 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/maxedapps/agent-skills/create-plan)<a href="https://agentmods.dev/skills/maxedapps/agent-skills/create-plan"><img src="https://agentmods.dev/badge/skills/maxedapps/agent-skills/create-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/maxedapps/agent-skills/create-plan"><img src="https://agentmods.dev/badge/skills/maxedapps/agent-skills/create-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 | $0.00068 | $0.00536 |
| Opus 5.5 | $0.00027 | $0.00214 |
| Sonnet 5.5 | $0.00014 | $0.00107 |
| Haiku 4.5 | $0.00007 | $0.00054 |
Grade A, and why
create-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 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.
What it actually says
Create Plan
Plan only; don't implement.
Files
Decisions and their plans live together in the project's adrs/ folder. If the project already uses a different ADR layout, follow it.
adrs/NNNN-<slug>.md: the decision. Use the next free number and never renumber.adrs/NNNN-<slug>.plan.md: the plan that implements that decision.
Small changes that involve no real decision need neither. Just do them, or agree on the approach in chat.
The ADR
Keep it short, usually under a page:
- Status: Proposed, Accepted, or Superseded by NNNN
- Context: the problem and its constraints
- Decision: what we'll do
- Alternatives: always include the simplest option that could work, and say why it was or wasn't chosen
- Consequences: the trade-offs we accept
Write new ADRs as Proposed. Mark one Accepted only when the user approves it. When a decision changes, write a new ADR that supersedes the old one instead of rewriting accepted history.
The plan
- Status: Draft, Ready, In progress, or Done
- Goal: what's done when we're done, and what's out of scope
- Tasks: in order. For each task, say what changes and where to start, how to verify it, and whether it's done. Verification means the high-value tests to add or run, plus manual checks where they matter (e.g. agent-browser for UI).
- Open questions: anything the user must decide
Keep it simple
- Research the code and docs as much as the plan needs, and no more.
- Pick the simplest design that meets the goal. Add no speculative options, fallbacks, abstractions, or "later" tasks.
- Before saving, remove every task that doesn't serve the goal.
- When a choice about scope, behavior, or architecture is genuinely ambiguous, ask the user instead of guessing.
- Challenge every piece of feedback on a plan: does it fix a real, likely problem, or does it just add complexity? When unsure, ask the user.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · -18 lines · -18 tokens per session 6063543bc580
- 1mo ago Changed · -1 lines 4fd5d8b8a6f6
- 1mo ago Changed · +3 lines 6c62298e406e
- 2mo ago First seen · 66 lines · 86 tokens per session scan A fab586e4b944
create-plan is a skill published in the GitHub repository maxedapps/agent-skills (60 stars, last pushed 1mo ago), licensed MIT. It adds 68 tokens to every session and 536 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 2026-08-30.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…