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/ffleurey/mcpscope/agents-mdgit clone --depth 1 https://github.com/ffleurey/mcpscopeWhat 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 | $0.01894 | $0.01894 |
| Opus 5 | $0.00947 | $0.00947 |
| Sonnet 5 | $0.00379 | $0.00379 |
| Haiku 4.5 | $0.00189 | $0.00189 |
Grade A, and why
mcpscope 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 2d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
mcpscope Agent Guide
This guide is for agents working on mcpscope's own code. If you are an agent (or configuring one) using mcpscope to test an MCP server, you want MCP.md and EXAMPLE.md instead — mcpscope speaks MCP itself.
mcpscope is a backend-centered runtime analysis tool for MCP and multi-turn LLM workflows. Optimize for correctness, inspectability, and parity across the backend API, CLI, MCP interface, and thin Svelte frontend.
Fast Start
Read only what the task needs:
- README.md for the product overview and the Documentation index of every doc — start there if the right file isn't listed below; DEVELOPMENT.md for run-from-source and dev commands
- ARCHITECTURE.md for runtime flow, persistence, execution, and adapters
- DATA-MODEL.md for sessions, turns, rounds, parts, and canonical IDs
- DATABASE-SCHEMA.md for the SQLite tables behind that model
- TESTING.md for regression strategy and test selection
- CLI.md and MCP.md for command and tool behavior
- BENCHMARK.md for the benchmark suite/case/run feature, deterministic metrics, and LLM rubric evaluation — the latter is implemented as a
benchmark_evaluationanalysis workflow (one judge session per run-session), so it shares the analysis subsystem rather than being a separate engine; treat the two as one mechanism when changing either - PROVIDERS.md when touching reasoning, token counting, or context-window handling across LM Studio / Ollama / OpenRouter
- DESIGN-SYSTEM.md before any frontend visual change — tokens, shared primitives, and patterns. Reuse the primitives; keep
DESIGN-SYSTEM.md,frontend/src/app.css, and the live Design System Reference (DesignReference.svelte) in sync.
The docs above are references, not pre-read requirements. Keep context lean and open only the specific files needed for the task at hand.
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.
- 2d ago First seen · 115 lines · 1,894 tokens per session scan A 13d5882a4077
mcpscope AGENTS.md is an instructions file published in the GitHub repository ffleurey/mcpscope (2 stars, last pushed 4d ago), licensed Apache-2.0. It adds 1,894 tokens to every session, about $0.0095 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
agentic-vbench AGENTS.md
Instructions for PhiloLabs/agentic-vbench, covering agents.md, start, map, docs and code.
benchjack CLAUDE.md
Instructions for benchjack/benchjack, covering claude.md, project overview, tech stack, repository layout and common commands.
finreportbench AGENTS.md
Instructions for MisterBrookT/finreportbench, covering finreportbench agent handoff, mission, start here, repository map and dataset contract.
agentic-vbench CLAUDE.md
Instructions for PhiloLabs/agentic-vbench, a project described as: AgenticVBench: Can AI Agents Complete Real-World Post-Production Tasks?
Sponsio CLAUDE.md
Instructions for SponsioLabs/Sponsio, covering agent guide for sponsio, what sponsio is, positioning, what to read first and repository map.
gini-agent AGENTS.md
AGENTS.md instructions for Open-Curiosity/gini-agent, covering gini agent instructions, shape, adrs, boundaries and branches.