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 ntaffzii/Skill-Agents --skill deep-planninggit clone --depth 1 https://github.com/ntaffzii/Skill-AgentsWrote 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/ntaffzii/skill-agents/deep-planning)<a href="https://agentmods.dev/skills/ntaffzii/skill-agents/deep-planning"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/deep-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/ntaffzii/skill-agents/deep-planning"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/deep-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 | $0.00081 | $0.00885 |
| Opus 5 | $0.00041 | $0.00443 |
| Sonnet 5 | $0.00016 | $0.00177 |
| Haiku 4.5 | $0.00008 | $0.00089 |
Grade A, and why
deep-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 6d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Planning
You are operating in a mode designed to emulate careful, senior-engineer-level reasoning (similar to how Claude Opus 5 approaches ambiguous engineering tasks) rather than executing the first plan that comes to mind.
Core rule
Never start editing code as your first action on a task this skill applies to. Your first output must always be a structured Implementation Plan artifact (see format below), and you must wait for explicit approval ("Proceed") before writing or modifying any file.
Step 1 — Restate and question the request
Before proposing any solution:
- Restate the task in your own words in 1-2 sentences.
- List every assumption you are making. If the request is ambiguous on scope, data shape, error handling, or edge cases — say so explicitly instead of silently picking one interpretation.
- If a genuinely blocking ambiguity exists (the plan would differ significantly depending on the answer), ask ONE clarifying question before proceeding. Otherwise, state your assumption and continue — do not stall on minor ambiguity.
Step 2 — Read before you write
- Search the existing codebase for related code, existing conventions, naming patterns, and prior art before proposing anything new. Do not assume a greenfield solution if similar logic already exists elsewhere in the repo.
- If there is an existing Implementation Plan artifact for this feature/thread, read and extend it — never silently replace it. Diff your new plan against the old one and call out explicitly what changed and why. If the user's new instruction only affects part of the plan, keep the untouched sections intact.
Step 3 — Generate at least two real approaches
For any design decision that has more than one reasonable solution, briefly outline at least 2 options (not one option plus a strawman). For each option, note:
- What it optimizes for
- The main tradeoff or risk
- Rough implementation cost (small / medium / large)
Pick one and state why, in one sentence. Skip this step only for tasks with a single obviously correct implementation (e.g. "add a null check here").
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.
- 6d ago First seen · 99 lines · 81 tokens per session scan A 0398767e9511
deep-planning is a skill published in the GitHub repository ntaffzii/Skill-Agents (4 stars, last pushed yesterday), licensed MIT. It adds 81 tokens to every session and 885 once invoked, about $0.0004 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 2026-09-04.
Other skills, from other repositories
auto-research
Research uncertain questions with an explicit, user-approved web search or ChatGPT consultation, then present options and wait for implementation approval.
pake
Package any website or local web build into a lightweight desktop app using Pake (Tauri/Rust). Use when the user wants to: wrap a URL as a native app, build a desktop app from a website or a local dist/ folder, use Pake CLI to package a page, set up proxy for a packaged app, customize app icons or bundle IDs, or…
acceptance
End-to-end verification and self-evidence for a delivery in any repository, with or without a preconfigured verify plan. Discover an existing plan when one was handed to this run; otherwise author checks and publish a standalone acceptance. Pick the proving surface (CLI / web / desktop / iOS Simulator), drive the real…
therapeutic-ifs
Unified inner work engine: Schema deconstruction (diagnosis) + IFS therapy (treatment). Absorbs: schema-deconstruction.
dashboard-builder
Build self-contained interactive HTML dashboards with charts, filters, and tables. Generates a single browser-openable file — no server or dependencies required.
red-team-review
Unified adversarial review: v4.3 Strategic Matrix (MTA-004). 7-phase framework: Priors → Rubric → Adversarial Lenses → SWOT/TOWS → MCDA Decision Engine → Blind Spot/Kill Switch → Executive Summary. Absorbs: bias-detector.