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/smaramwbc/statewave-multi-agent-shared-context/agents-mdgit clone --depth 1 https://github.com/smaramwbc/statewave-multi-agent-shared-contextWrote 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/smaramwbc/statewave-multi-agent-shared-context/agents-md)<a href="https://agentmods.dev/instructions/smaramwbc/statewave-multi-agent-shared-context/agents-md"><img src="https://agentmods.dev/badge/instructions/smaramwbc/statewave-multi-agent-shared-context/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 | $0.00380 | $0.00380 |
| Opus 5 | $0.00190 | $0.00190 |
| Sonnet 5 | $0.00076 | $0.00076 |
| Haiku 4.5 | $0.00038 | $0.00038 |
Grade A, and why
statewave-multi-agent-shared-context 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 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.
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
Statewave project memory
This workspace has a Statewave “project brain” exposed over MCP (server id: statewave). It holds this project's summary, conventions, documentation, git history, code structure and remembered facts, scoped to subject repo:smaramwbc.statewave-multi-agent-shared-context.
Read it first
Before answering questions about THIS project — conventions, architecture, history, structure, prior decisions, “how/why does X work”, “what changed” — call the statewave_get_context MCP tool (subject repo:smaramwbc.statewave-multi-agent-shared-context, query = the user's ask) and ground your answer in what it returns. Prefer it over guessing or re-deriving from scratch.
Persist durable facts
When the user states a durable preference, decision, or fact worth remembering across sessions (e.g. “my favorite color is red”, “we use X for Y”, “always do Z here”), call the statewave_ingest_episode MCP tool (subject repo:smaramwbc.statewave-multi-agent-shared-context, kind chat.note, text = the fact). Capture stable facts/preferences/decisions only — not transient chatter, and not code you are about to write. The user sees and can approve each tool call.
Immediately after a successful statewave_ingest_episode, call the statewave_compile_subject MCP tool (subject repo:smaramwbc.statewave-multi-agent-shared-context). An ingested episode is raw and not yet retrievable; compiling distils it into the durable memory that statewave_get_context returns next time.
Never invent Statewave results; if the tool is unavailable, say so plainly.
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 · 18 lines · 380 tokens per session scan A 0fe5eebbe9dd
statewave-multi-agent-shared-context AGENTS.md is an instructions file published in the GitHub repository smaramwbc/statewave-multi-agent-shared-context (44 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 380 tokens to every session, about $0.0019 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 2026-08-30.
Other instructions, from other repositories
commonly AGENTS.md
AGENTS.md instructions for Team-Commonly/commonly, a project described as: Open-source room for humans + cross-vendor AI agents. Every agent gets its own name, memory, skills, and workstation. Any runtime, your infra — no per-agent fees.
wiii CLAUDE.md
Claude Code instructions for meiiie/wiii, a project described as: Wiii is an open-source durable AI workbench for conversations, local and cloud agents, files, tools, memory, artifacts, and permission-aware integrations.
commonly CLAUDE.md
Claude Code instructions for Team-Commonly/commonly, covering claude.md / agents.md, 🧠 product vision & architecture philosophy, what commonly is, the architecture model and key concepts.
honcho CLAUDE.md
Claude Code instructions for plastic-labs/honcho, covering claude.md, honcho overview, what is honcho?, core concepts and peer paradigm.
research-os AGENTS.md
Instructions for lxinfei5/research-os, covering researchos — constitution, §0 what this is, §1 directory discipline, §2 half-life (innovation 1) — memory design and §3 behavior pillars (innovations 2–5).
basic-memory CLAUDE.md
Claude Code instructions for basicmachines-co/basic-memory, a project described as: AI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN.