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/anthroos/openexp/claude-mdgit clone --depth 1 https://github.com/anthroos/openexpWhat 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 | $0.00799 | $0.00799 |
| Opus 5 | $0.00400 | $0.00400 |
| Sonnet 5 | $0.00160 | $0.00160 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
openexp 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 yesterday.
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 — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenExp — Development Instructions
Memory Protocol (MANDATORY)
OpenExp gives Claude Code persistent memory: hybrid retrieval (vector + BM25), prediction-outcome feedback, and the experience-pack pipeline. For the system to learn from your work, follow this protocol every task:
Before starting any task:
search_memory("relevant context for this task")
Find prior experience, decisions, mistakes. Hooks do auto-recall on each message, but you MUST do a targeted search before complex tasks.
After completing a task:
add_memory("what was decided/done and why", type="decision")
Capture outcomes, not just actions. The prediction loop (below) cannot reward retrieval if the outcome was never written down.
When the user shares context:
add_memory("the context", type="fact")
Immediately. Don't wait. Every piece of context improves future retrieval.
Prediction loop (build judgment over time):
When you make a prediction or recommendation (deal outcome, approach success, client reaction):
log_prediction("prediction text", confidence=0.7, memory_ids=["ids-that-informed-this"])
Later, when the outcome is known:
log_outcome(prediction_id="pred_xxx", outcome="what happened", reward=0.8)
This is the active feedback path — verified outcomes flow back to the memories that informed them. Use for: deal predictions, strategy recommendations, client behavior forecasts, technical approach bets.
Architecture
Full reference: docs/storage-system.md for retrieval/scoring details, docs/experience-library.md for the Experience Library pipeline.
openexp/core/— search, scoring, lifecycle, storageopenexp/ingest/— Transcript ingest + Experience Library pipeline (chunking, topic mapping, experience extraction)openexp/mcp_server.py— MCP STDIO server (5 tools: search_memory, add_memory, log_prediction, log_outcome, memory_stats)openexp/cli.py— CLI (search, ingest, chunk, topics, stats, compact, experience, viz)scripts/batch_label.py— Batch experience labeling across all threadstests/— 300 tests across 13 files
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.
- yesterday First seen · 78 lines · 799 tokens per session scan A 95ce8604737d
openexp CLAUDE.md is an instructions file published in the GitHub repository anthroos/openexp (59 stars, last pushed 3mo ago), licensed MIT. It adds 799 tokens to every session, about $0.0040 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
m_flow AGENTS.md
AGENTS.md instructions for FlowElement-xinliuyuansu/m_flow, covering m-flow — developer & agent reference, 1. repository map, extension points, 2. local development and python backend (requires python 3.10 – 3.13).
senpi AGENTS.md
Instructions for code-yeongyu/senpi, covering senpi repository guide, mandatory execution protocols — non-negotiable, protocol 1 — explicitly requested modifications, protocol 2 — user-requested pr reviews and structure.
easy-notion-mcp CLAUDE.md
Instructions for Grey-Iris/easy-notion-mcp, covering easy-notion-mcp, open source context, .meta/ publication policy (hybrid, 2026-07-02), standing priorities and commands.
adeu GEMINI.md
Instructions for dealfluence/adeu, covering adeu — native track changes for ai, available tools, readdocx, processdocumentbatch and applytextrevision.
Guanlan CLAUDE.md
Instructions for shenyangs/Guanlan, covering claude.md, project, durable memory surfaces, development commands and core structure.
openings-mcp AGENTS.md
Instructions for amikai/openings-mcp, a project described as: 💼 One MCP server to search job boards and company career sites.