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 instructions/frostney/pascal-mcp-sdk/agents-mdgit clone --depth 1 https://github.com/frostney/pascal-mcp-sdkWrote 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/instructions/frostney/pascal-mcp-sdk/agents-md)<a href="https://agentmods.dev/instructions/frostney/pascal-mcp-sdk/agents-md"><img src="https://agentmods.dev/badge/instructions/frostney/pascal-mcp-sdk/agents-md.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 | $0.02569 | $0.02569 |
| Opus 5 | $0.01285 | $0.01285 |
| Sonnet 5 | $0.00514 | $0.00514 |
| Haiku 4.5 | $0.00257 | $0.00257 |
Grade A, and why
pascal-mcp-sdk AGENTS.md 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 3d 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 — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Hard Constraints
- FreePascal only. FPC 3.2.2, Delphi mode, flags centralised in
source/units/Shared.inc. Do not introduce another compiled language or repeat compiler directives per unit. - Zero third-party runtime dependencies. The library is RTL + fpjson
only. Packages that ship inside FPC 3.2.2 are not third-party: fcl-web
is admitted on the same footing as fcl-json (fpjson), and stays
confined to
MCP.Transport.HTTP. lwpt'stestingpackage is dev-time; anything beyond that needs explicit maintainer approval with a recorded justification. - lwpt is the only toolchain entry point — install, build, test, format
all go through it. Do not add another build system (no Make/CMake for
builds) and do not invoke
fpcdirectly except asfpc @lwpt.cfg. lwpt.cfgandlwpt.lockare generated bylwpt install; never hand-edit them.lwpt.tomlis the manifest you edit.- The
unitsarray inlwpt.tomllists onlysource/units— lwpt (0.2.0+) discovers dep units through nested manifests. Keep[format] exclude = [".lwpt/**"]so the formatter never rewrites fetched modules. - Layout is fixed: library units in
source/units/(namespacedMCP.*.pas, tests co-located asMCP.*.Test.pas), program entry points insource/apps/, self-contained run-script wrappers inscripts/(InstantFPC-executed, so noShared.incand noMCP.*units there). build/is generated — never commit it.MCP.Serverowns the protocol surface. Dispatch rules, error codes, and result shapes must not leak into transports; transports move lines only.MCP.Protocolowns the per-request_metamodel;MCP.JSONRPCowns the JSON-RPC 2.0 profile.- Spec facts are verified, never recalled. Any change to protocol behaviour cites the official spec page (modelcontextprotocol.io) it implements, with the verification date — see the unit headers and docs/internals/architecture.md for the pattern.
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.
- 3d ago First seen · 148 lines · 2,569 tokens per session scan A 91c5fcff03b6
pascal-mcp-sdk AGENTS.md is an instructions file published in the GitHub repository frostney/pascal-mcp-sdk (2 stars, last pushed 8d ago), licensed MIT. It adds 2,569 tokens to every session, about $0.0128 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 instructions, from other repositories
GocciaScript AGENTS.md
AGENTS.md instructions for frostney/GocciaScript, covering agents.md, contributing guide vs this file, expectations for assistants, tc39 spec lookup and quick checks.
GocciaScript CLAUDE.md
Claude Code instructions for frostney/GocciaScript, a project described as: A drop of JavaScript — a JavaScript engine and sandbox-first ECMAScript runtime implemented in Object Pascal.
llm-context.py CLAUDE.md
Instructions for cyberchitta/llm-context.py, covering claude.md, working notes (gitignored) and draining the field notes.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
Plonk AGENTS.md
AGENTS.md instructions for ostapondo/Plonk, covering agent rules, layout, adding a module, build & verify and code style.