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 tallesborges/zdx --skill ship-first-plangit clone --depth 1 https://github.com/tallesborges/zdxWrote 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/tallesborges/zdx/ship-first-plan)<a href="https://agentmods.dev/skills/tallesborges/zdx/ship-first-plan"><img src="https://agentmods.dev/badge/skills/tallesborges/zdx/ship-first-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/tallesborges/zdx/ship-first-plan"><img src="https://agentmods.dev/badge/skills/tallesborges/zdx/ship-first-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 | $0.00056 | $0.01552 |
| Opus 5 | $0.00028 | $0.00776 |
| Sonnet 5 | $0.00011 | $0.00310 |
| Haiku 4.5 | $0.00006 | $0.00155 |
Grade A, and why
ship-first-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 8d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship-First Plan
Goal
Create the smallest grounded plan that reaches the first usable version of the requested capability through demoable, incremental phases.
Hard constraints
- Stop at usable: plan through the first usable version of the capability, ordered by real dependencies.
Laterholds rollout, hardening, polish, and follow-on capabilities as one-liners with triggers. Correctness and security for the behavior you ship belong in the phase that ships it. - One behavior per phase: each phase adds one capability or changes one observable behavior. Its checklist items build that behavior; its ✅ Demo exercises it and states the observed result. Multi-step setup is fine when it proves a single new outcome; two new outcomes are two phases.
- Bounded exit each: each phase is work you intend now and has a bounded exit. Conditional work lives in
Laterwith the trigger that would start it. - Gates attach to their phase: approvals, ownership questions, and research attach as a gate note on the phase they block; the phase's ✅ Demo stays an observation of system behavior.
- Smallest implementation: a phase's abstractions, config, schema, flags, and interfaces are paid for by the behavior it ships. Shared code moves to a shared home once a second consumer exists.
- Reuse before rebuild: before proposing a new module, config, schema, or abstraction, explore the codebase for existing functionality/patterns that already do it (or most of it). Extend what exists rather than standing a parallel implementation beside it.
- Scope from Inputs: build the capabilities present in the Inputs, using the illustrative examples the Inputs provide.
Workflow
Operate read-only while researching and drafting — the only file you create is the saved plan itself (step 6).
Delegation guard: a delegated drafter gets these Hard constraints, the template below, and a brief carrying five things — the goal, the current state, the constraints, the success signal, and the code findings that change what you would build. That brief is complete on its own.
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.
- 8d ago First seen · 108 lines · 56 tokens per session scan A 330a729e33c7
ship-first-plan is a skill published in the GitHub repository tallesborges/zdx (20 stars, last pushed 4d ago), licensed MIT. It adds 56 tokens to every session and 1,552 once invoked, about $0.0003 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…