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 mnthe/hardworker-marketplace --skill planninggit clone --depth 1 https://github.com/mnthe/hardworker-marketplaceWrote 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/mnthe/hardworker-marketplace/planning)<a href="https://agentmods.dev/skills/mnthe/hardworker-marketplace/planning"><img src="https://agentmods.dev/badge/skills/mnthe/hardworker-marketplace/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/mnthe/hardworker-marketplace/planning"><img src="https://agentmods.dev/badge/skills/mnthe/hardworker-marketplace/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 | $0.00044 | $0.02181 |
| Opus 5 | $0.00022 | $0.01091 |
| Sonnet 5 | $0.00009 | $0.00436 |
| Haiku 4.5 | $0.00004 | $0.00218 |
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 — 273 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Planning Protocol
Overview
Define how to analyze context, make design decisions, and decompose work into tasks.
Two modes:
- Interactive: Orchestrator conducts Deep Interview for decisions
- Auto: Planner agent makes decisions based on context alone (--auto or --skip-interview)
Phase 1: Read Context
Read session files in order:
session.json- goal and metadatacontext.json- summary, key files, patterns from explorersexploration/*.md- detailed findings as needed
Phase 2: Complexity Analysis
Analyze goal and context to determine interview depth:
| Complexity | Files | Keywords | Impact | Rounds |
|---|---|---|---|---|
| trivial | 1-2 | fix, typo, add | None | 1 (4-5 Q) |
| standard | 3-5 | implement, create | Single module | 2 (8-10 Q) |
| complex | 6-10 | refactor, redesign | Multi-module | 3 (12-15 Q) |
| massive | 10+ | migrate, rewrite | Entire system | 4 (16-20 Q) |
Note: User can request more rounds via adaptive check. No upper limit.
Phase 3: Deep Interview (Interactive Mode)
Skip if: --auto or --skip-interview flag set
Interview Structure
Each round asks 4-5 questions using AskUserQuestion (max 4 questions per call).
Context-Aware Options (CRITICAL)
Options marked [...] MUST be generated from exploration context, NOT generic templates.
See references/context-aware-options.md for:
- Generation process from context.json and exploration/*.md
- Option generation rules by question type
- Context-aware vs generic examples
- Validation checklist
Data-Driven Interview Questions
Interview questions must be generated from exploration data, not generic templates.
Question Generation Rules
BAD (generic): "어떤 아키텍처 패턴을 사용할까요?" GOOD (data-driven): "graph/service.go가 2곳에서 사용됩니다. 두 곳 모두 동시에 변경할까요?"
Formula: [탐색에서 발견한 사실] + [그로 인한 설계 선택지] + [각 선택지의 trade-off]
Interview Question → Design Section Mapping
| Question Category | Design Section |
|---|---|
| "어떤 접근법?" | Approach Selection, Decisions |
| "영향 범위는?" | Impact Analysis |
| "성공 기준은?" | Verification Strategy |
| "위험 요소는?" | Assumptions & Risks |
| "테스트 방법은?" | Verification Strategy |
What ships with it
5 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.
- 10d ago First seen · 273 lines · 44 tokens per session scan A 4ff41a266237
planning is a skill published in the GitHub repository mnthe/hardworker-marketplace (4 stars, last pushed 4mo ago), licensed MIT. It adds 44 tokens to every session and 2,181 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 2026-08-31.
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…