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/rul1an/assay/claude-mdgit clone --depth 1 https://github.com/Rul1an/assayWrote 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/rul1an/assay/claude-md)<a href="https://agentmods.dev/instructions/rul1an/assay/claude-md"><img src="https://agentmods.dev/badge/instructions/rul1an/assay/claude-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 5.1 | $0.04570 | $0.04570 |
| Opus 5 | $0.02285 | $0.02285 |
| Sonnet 5 | $0.00914 | $0.00914 |
| Haiku 4.5 | $0.00457 | $0.00457 |
Grade A, and why
assay CLAUDE.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 today.
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 — 346 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assay - AI Agent Context
Cross-agent work must first read and follow AGENTS.md. That file is the shared source of truth for branch ownership, ADR-042/043 scope, review quorum, and verification. This file adds Assay-specific technical context and does not override that contract.
What is Assay?
Assay is a Policy-as-Code engine for Model Context Protocol (MCP) that validates AI agent behavior. It provides deterministic testing (trace replay), runtime security (eBPF/LSM kernel enforcement on Linux), and policy gates (tool argument/sequence validation).
Workspace Structure
Rust monorepo, workspace version 6.1.0, 22 workspace packages (21 under crates/ plus
assay-python-sdk; 7 are publish = false). Curated view, grouped by role:
crates/
# Core engine + CLI
assay-core/ Core evaluation engine (Runner, Store, MCP, Trace, Report, Providers, VCR, Replay Bundle)
assay-cli/ CLI binary ("assay") - all user-facing commands
assay-metrics/ Standard metrics (MustContain, RegexMatch, ArgsValid, SequenceValid, etc.)
assay-common/ Shared types (no_std compatible for eBPF)
assay-canonical/ Deterministic canonicalization: RFC 8785 (JCS) bytes, sha256 content IDs, semantic digests
# Evidence + distribution
assay-evidence/ Evidence bundles (tar.gz with manifest.json + events.ndjson), lint, diff, sanitize
assay-registry/ Pack Registry client (HTTP, DSSE verification, OIDC auth, local caching, lockfile v2)
gateway-evidence-replay/ Deterministic replay verifier for gateway-path evidence bundles (standalone)
# Policy + runtime enforcement
assay-policy/ Policy compilation (Tier 1: kernel, Tier 2: userspace)
assay-mcp-server/ MCP server/proxy for runtime policy enforcement (JSON-RPC over stdio)
assay-monitor/ Runtime eBPF/LSM monitoring (Linux only)
assay-ebpf/ Kernel eBPF programs (LSM hooks + tracepoints)
# Measured-run substrate (internal/experimental "Assay-Runner", API unstable)
assay-runner-core/ Runner orchestration, archive assembly, layer normalizers
assay-runner-linux/ Linux-only platform adapter, cgroup placement primitives
assay-runner-schema/ Versioned schema types + constants for Runner v0 contracts
# Protocol adapters (evidence translation)
assay-adapter-api/ Adapter API contracts (shared trait surface)
assay-adapter-a2a/ A2A protocol adapter
assay-adapter-acp/ ACP protocol adapter
assay-adapter-ucp/ UCP protocol adapter
# Simulation + tooling
assay-sim/ Attack simulation harness (chaos, differential, integrity testing)
assay-xtask/ Build tooling
assay-python-sdk/ Python SDK (PyO3 bindings + pytest plugin; crate name "assay-it")
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.
- today Changed 00a3dbb7437f
- yesterday Changed · +4 lines · +46 tokens per session 2abd37cf4c2a
- 6d ago First seen · 342 lines · 4,524 tokens per session scan A 86d5740831bf
assay CLAUDE.md is an instructions file published in the GitHub repository Rul1an/assay (10 stars, last pushed yesterday), licensed MIT. It adds 4,570 tokens to every session, about $0.0229 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
toolhive-studio copilot-instructions.md
Copilot instructions for stacklok/toolhive-studio, covering instructions for copilot, ui components, data fetching, file naming conventions and testing.
toolhive-studio CLAUDE.md
Claude Code instructions for stacklok/toolhive-studio, covering project overview, build and development commands, environment requirements, common gotchas and auto-generated code — never edit manually.
toolhive-studio AGENTS.md
AGENTS.md instructions for stacklok/toolhive-studio, covering project overview, essential commands, common gotchas, boundaries and code conventions.
agent-security-scanner-mcp CLAUDE.md
Claude Code instructions for sinewaveai/agent-security-scanner-mcp, covering claude.md, build and development commands, install dependencies, run all tests (28 test files, 420+ tests, 4.5 min) and run specific test file.
rust-sdk fetch-mcp-doc.instructions.md
Instructions for modelcontextprotocol/rust-sdk, covering overall, key changes, architecture, baseprotocol and lifecycle.
m1nd AGENTS.md
AGENTS.md instructions for maxkle1nz/m1nd, covering agents.md — working guide for any coding agent on m1nd, the gates (must pass — these are the ci), git identity — absolute, no-leak — reputation rule (public repo) and how work lands — bursts, not pr-per-fix.