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/takeyaqa/pictmcp/agents-mdgit clone --depth 1 https://github.com/takeyaqa/PictMCPWrote 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/takeyaqa/pictmcp/agents-md)<a href="https://agentmods.dev/instructions/takeyaqa/pictmcp/agents-md"><img src="https://agentmods.dev/badge/instructions/takeyaqa/pictmcp/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 | $0.00504 | $0.00504 |
| Opus 5 | $0.00252 | $0.00252 |
| Sonnet 5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
PictMCP 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.
What it actually says
Agent Instructions for PictMCP
Overview
PictMCP is an MCP (Model Context Protocol) server that provides pairwise combinatorial testing via WebAssembly-compiled PICT. It exposes a generate-test-cases tool for AI assistants. It uses @takeyaqa/pict-wasm to generate combinatorial test cases.
Build and Test Commands
# Install dependencies
pnpm install
# Compile TypeScript to dist/
pnpm run build
# Lint and format
pnpm run fmt
pnpm run lint
pnpm run typecheck
# Run all tests once
pnpm run test:run
Architecture
src/index.ts- Entry point; creates server and connects via stdio transportsrc/server.ts- MCP server definition withgenerate-test-casestool registrationtests/e2e.spec.ts- End-to-end tests using in-memory MCP transportserver.json- MCP server manifest (version must stay in sync with package.json)
The server uses @modelcontextprotocol/sdk for MCP protocol handling and @takeyaqa/pict-wasm for the PICT algorithm.
Key Conventions
- Git Workflow: Always create a new branch from
mainbefore starting any task - Zod for schemas: Tool input/output schemas use Zod v4 with
.describe()for documentation - Version sync:
versioninpackage.json,server.json, andsrc/server.tsmust match - ES modules: Project uses
"type": "module"with.jsextensions in imports - Strict TypeScript -
tseslint/strictTypeCheckedfor source,tseslint/recommendedfor tests - Prettier for formatting
- Commit Messages: Use Conventional Commits format (e.g.,
feat:,fix:,docs:,chore:,refactor:,test:,ci:) - Before committing - Always run
pnpm run fmt,pnpm run lint,pnpm run typecheck, andpnpm run test:run - Ignore
pnpm-lock.yaml- Always skip this file during code review and pull request creation
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 · 45 lines · 504 tokens per session scan A b8d1c09e4194
PictMCP AGENTS.md is an instructions file published in the GitHub repository takeyaqa/PictMCP (0 stars, last pushed 5mo ago), licensed MIT. It adds 504 tokens to every session, about $0.0025 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
keploy AGENTS.md
AGENTS.md instructions for keploy/keploy, covering agents.md, what this project is, build, run, lint, test, build the binary and standard build (what ci calls "build-no-race").
antigravity-testing-kit GEMINI.md
Instructions for anhtester/antigravity-testing-kit, covering gemini ai - global automation agent rules, git pull restriction rule, browser rules (mandatory), 🖥️ viewport & mode and 🔄 thứ tự debug bắt buộc (playwright mcp).
testkube AGENTS.md
AGENTS.md instructions for kubeshop/testkube, covering working with testkube core (testkube), deprecated components — do not reference, purpose, entry points and mcp integration.
sensei AGENTS.md
Instructions for spboyer/sensei, covering agents.md, repository structure, key conventions, skill.md format and skill body (markdown).
sensei copilot-instructions.md
Instructions for spboyer/sensei, covering copilot instructions, project context, skill authoring rules, token and scoring expectations and validation commands.
direct AGENTS.md
Instructions for hraness/direct, a project described as: A TypeScript harness for deterministic frontend development with repeatable scenarios, local fixtures, and browser verification for coding agents.