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 scott-fryxell/brayness --skill planninggit clone --depth 1 https://github.com/scott-fryxell/braynessWrote 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/scott-fryxell/brayness/planning)<a href="https://agentmods.dev/skills/scott-fryxell/brayness/planning"><img src="https://agentmods.dev/badge/skills/scott-fryxell/brayness/planning/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/scott-fryxell/brayness/planning"><img src="https://agentmods.dev/badge/skills/scott-fryxell/brayness/planning.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 | $0.00114 | $0.02193 |
| Opus 5 | $0.00057 | $0.01097 |
| Sonnet 5 | $0.00023 | $0.00439 |
| Haiku 4.5 | $0.00011 | $0.00219 |
Grade A, and why
planning 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 10d 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 — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planning
Plan work as a directed acyclic graph before doing it. The DAG is the Planner step from the harness article; brayness's plan doc inverts it - the agent proposes, you approve, then execution runs. This skill never runs a crew solo.
Roles -> one identity per phase
The arc as five fixed roles, used by name across this skill and AGENTS.md:
- Explorer - figure out what the task really is. Only phase where digging is the right move; skip it once the ask is clear.
- Planner - shape branchy work into a DAG and stop at Gate 1. Trivial or linear work skips the planner and passes straight through.
- Worker - run nodes in topological order; plain execution is the default.
- Critic - verify each node's output, cheapest deterministic check first.
- Promoter - decide if verified work is worth showing off; most nodes never earn it.
Keep the names fixed (Explorer, Planner, Worker, Critic, Promoter) in docs, plans files, and habit references — no "research phase" or "promote step" aliases.
When to use
- Work that branches, rejoins, or explodes like a mind map or creative project.
- Several pieces of work with dependencies between them.
- A task big enough that "just do it" would bury its own shape.
Skip it for trivial or purely linear tasks - planning has a cost, spend it where it pays.
Core rule: the graph is the plan, you are the gate
The DAG is a directed acyclic graph: nodes are units of work, edges are dependencies. Build the graph, then check in with you at each decision gate. You approve before anything executes. The agent never self-runs the whole DAG.
Process
1. Planner - build the DAG
- List every unit of work as a node: id, one-line goal, effort (cheap/medium/expensive).
- Draw edges only where one node actually depends on another.
- Keep it a DAG - no cycles. A cycle means the plan is muddled; break it.
- Aim for small nodes that parallelize cleanly. Split anything that would become a paragraph to describe.
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.
- 10d ago First seen · 221 lines · 114 tokens per session scan A e9f5483b8aa2
planning is a skill published in the GitHub repository scott-fryxell/brayness (120 stars, last pushed yesterday), licensed MIT. It adds 114 tokens to every session and 2,193 once invoked, about $0.0006 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…