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 maludb-ed/htmx-php-builder --skill memory-first-planninggit clone --depth 1 https://github.com/maludb-ed/htmx-php-builderWrote 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/maludb-ed/htmx-php-builder/memory-first-planning)<a href="https://agentmods.dev/skills/maludb-ed/htmx-php-builder/memory-first-planning"><img src="https://agentmods.dev/badge/skills/maludb-ed/htmx-php-builder/memory-first-planning.svg" alt="Measured on agentmods" 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 | $0.00079 | $0.00546 |
| Opus 5 | $0.00039 | $0.00273 |
| Sonnet 5 | $0.00016 | $0.00109 |
| Haiku 4.5 | $0.00008 | $0.00055 |
Grade A, and why
memory-first-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 7d 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 — 21 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory-first planning context
The files in this skill give you context about the kind of application being planned. They are answers to questions you may have while planning — not a process to follow. Do not treat them as a workflow, a script, or a roadmap; do not walk the user through phases or checklists derived from them. Plan with the user however the conversation naturally goes, and consult these files when you need to know the direction of the project.
The three ideas
- Memory-first — an application is designed by deciding what it remembers before deciding what it does. The memory model comes first; features are views over memory. Full explanation: concepts/memory-first.md.
- Ask-me-anything — every SaaS application is secretly a knowledge base. A feature is a pre-packaged answer to a question someone asks the system, and planning is the work of discovering those questions. Full explanation: concepts/ask-me-anything.md.
- SaaS Plus+ (pronounced "SaaS Plus Plus") — a dedicated memory-first, ask-me-anything application in which each user or client gets a dedicated database and memory system. Built on sovereign data: clients can build and use AI systems without worrying that the SaaS provider will use their data to train additional models.
The technical stack
The stack is already decided — don't reopen it unless the user does. PostgreSQL 17 is the system of record; MaluDB is the activity memory, fed by application logs; the application baseline is Apache + PHP + Bootstrap 5.3 + HTMX, upgraded only when a concrete requirement demands it. Details, the two-memory architecture diagram, and the logging requirements: build/tech-stack.md.
Two kinds of questions, two memories: record questions ("which item sold the most last week?") are answered by agents reading PostgreSQL through MCP servers; activity questions ("when did Bob start planning for Oktoberfest?") are answered from application logs ingested into MaluDB. Activity memory cannot be backfilled — logging exists from day one.
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.
- 7d ago First seen · 21 lines · 79 tokens per session scan A c2fd4e8dee3b
memory-first-planning is a skill published in the GitHub repository maludb-ed/htmx-php-builder (8 stars, last pushed 1mo ago), licensed MIT. It adds 79 tokens to every session and 546 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 2026-08-31.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
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…