Borrowing it
Nothing to install: this file belongs to putervision/state-memory-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/putervision/state-memory-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/putervision/state-memory-mcpWrote 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/putervision/state-memory-mcp/claude-md)<a href="https://agentmods.dev/instructions/putervision/state-memory-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/putervision/state-memory-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/putervision/state-memory-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/putervision/state-memory-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.24821 | $0.24821 |
| Opus 5.5 | $0.09928 | $0.09928 |
| Sonnet 5.5 | $0.04964 | $0.04964 |
| Haiku 4.5 | $0.02482 | $0.02482 |
Grade B, and why
state-memory-mcp CLAUDE.md scanned grade B with 1 finding 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 1mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
* **Google Antigravity (`~/.gemini/config/config.json`)**: Add these rules to your `"globalPermissionGrants"` -> `"allow"` list: This is a copy
100% identical to state-memory-mcp copilot-instructions.md — 1 line differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 1,049 lines — stays where its author put it; the contents beside it link to each section on GitHub.
State Memory (state-memory-mcp)
This project tracks workflow state, tasks, design decisions, and blockers using state-memory-mcp with project slug "state-memory-mcp".
1. Priority Order
Before doing any coding or investigation:
manage_sessions(action: "start")— Start a tracking session for full change attribution.get_analytics(action: "summary")— Run to understand current project state, active branches, and overall progress.manage_tasks(action: "next")— Query prioritized runnable tasks.manage_tasks(action: "find_blockers")— Identify any active blockers preventing progress.manage_nodes(action: "list")— Find pending tasks, past decisions, or milestones.query_graph(action: "trace")— Trace what depends on or blocks a task.
2. When to Write to the Graph
You MUST update the graph as you work:
- Starting a session: Always call
manage_sessions(action: "start", agent_id: "my-agent")to track all mutations under a unique session. - Starting a new task: Create a node with
manage_nodes(action: "create", type: "task", title: "...", session_id: session_id). - Making a design or implementation decision: Document it with
manage_nodes(action: "create", type: "decision", title: "...", metadata: { "rationale": "..." }, session_id: session_id). - Connecting UI tasks to visual states: Use
manage_edges(action: "link_visual", target_id: task_id, visual_state_id: vs_id, relationship: "renders_state"). - Encountering a blocker: Record the blocker with
manage_nodes(action: "create", type: "blocker", ..., session_id: session_id)and connect it usingmanage_edges(action: "add", type: "blocks", source_id: blocker_id, target_id: task_id, session_id: session_id). - Adding observation notes: Atomically log notes using
manage_nodes(action: "add_note", text: "...", attach_to: node_id). - Batch updates: Bulk update tasks/nodes using
manage_nodes(action: "batch_update", ids: ["..."], status: "done"). - Observability & Trajectories: Check
manage_data(action: "export_synergy_metrics")for combined token savings & health, andmanage_data(action: "export_joint_trajectories")for interleaved fine-tuning datasets. - Completing a task: Update status to done using
manage_tasks(action: "complete", task_id: task_id). - Creating/generating a new file: Create an artifact node with
manage_nodes(action: "create", type: "artifact", ..., session_id: session_id)and connect it usingmanage_edges(action: "add", type: "produces", ..., session_id: session_id).
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.
- 1mo ago Changed · +216 lines · +5,298 tokens per session 8be6f5eb853e
- 1mo ago Changed · +221 lines · +5,406 tokens per session 81a1ec1c2783
- 1mo ago Changed · +396 lines · +9,713 tokens per session cea3e5fc47b0
- 1mo ago Changed · +134 lines · +2,583 tokens per session a18e0f58f7d2
- 2mo ago First seen · 82 lines · 1,821 tokens per session scan B 83ee082c70a6
state-memory-mcp CLAUDE.md is an instructions file published in the GitHub repository putervision/state-memory-mcp (42 stars, last pushed 1mo ago), licensed MIT. It adds 24,821 tokens to every session, about $0.0993 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 100% identical to state-memory-mcp copilot-instructions.md, differing in 1 line, and is treated as a copy.
state-memory-mcp CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| state-memory-mcp CLAUDE.mdputervision/state-memory-mcp | Instructions file | 42 | 1mo ago | MIT | B | 24,821 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |