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 agentmods add skills/maludb-ed/htmx-php-builder/mcp-serversnpx skills add maludb-ed/htmx-php-builder --skill mcp-serversgit 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/mcp-servers)<a href="https://agentmods.dev/skills/maludb-ed/htmx-php-builder/mcp-servers"><img src="https://agentmods.dev/badge/skills/maludb-ed/htmx-php-builder/mcp-servers.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 | $0.00081 | $0.01252 |
| Opus 5 | $0.00041 | $0.00626 |
| Sonnet 5 | $0.00016 | $0.00250 |
| Haiku 4.5 | $0.00008 | $0.00125 |
Grade A, and why
mcp-servers scanned grade A with 1 finding 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 4d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
rows = await db.fetch(FIND_CUSTOMER_SQL, params.query, params.limit) # read-only pool How it starts
The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory MCP Servers
Every application ships two MCP servers. They are designed with the schema in Phase 1 and are the only way agents read the memories — the AMA agent, the client's own AI tools, and future automations all go through them.
| Server | Name | Memory | Backing store |
|---|---|---|---|
| Record memory | {app}_records_mcp |
Entities, facts, current truth | PostgreSQL 17, read-only role |
| Activity memory | {app}_activity_mcp |
What happened, who, when | MaluDB, read-only role |
(A third, localhost-only server — {app}_actions_mcp for chat-driven navigation and actions — is specified in the chat-actions skill. This skill covers the two client-facing read servers; the read servers never write, and the actions server is never exposed.)
Designing the tool surface (Phase 1)
The tool surface is derived from the Phase 0 question list — features are pre-packaged answers to questions, and MCP tools are the same thing for agents.
- Purposeful tools first. Each recurring record question becomes a named tool (
find_customer,revenue_by_period,open_invoices_for); each recurring activity question becomes one on the activity server (actor_timeline,record_history,who_touched). Tool names are snake_case, action-oriented, and prefixed consistently. Descriptions state when to call the tool, not just what it does. - One guarded long-tail tool per server.
records_search/activity_searchaccepts a single SELECT statement, validated in code (reject anything else), run under the read-only role withstatement_timeoutand a row cap. The tool description embeds a schema summary so agents write correct queries. - Read-only, always. Every tool carries
readOnlyHint: true; no tool on either server ever writes. Writes happen only through the PHP application (which is what produces the activity log). - Filter and paginate. Tools return focused results with limit/offset or cursor parameters — never unbounded dumps.
Implementation (Python + FastMCP)
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.
- 4d ago First seen · 75 lines · 81 tokens per session scan A 9e6734c3e048
mcp-servers is a skill published in the GitHub repository maludb-ed/htmx-php-builder (8 stars, last pushed 29d ago), licensed MIT. It adds 81 tokens to every session and 1,252 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…