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/rahult18/prism-mem/agents-mdgit clone --depth 1 https://github.com/rahult18/prism-memWrote 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/rahult18/prism-mem/agents-md)<a href="https://agentmods.dev/instructions/rahult18/prism-mem/agents-md"><img src="https://agentmods.dev/badge/instructions/rahult18/prism-mem/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 | $0.00400 | $0.00400 |
| Opus 5 | $0.00200 | $0.00200 |
| Sonnet 5 | $0.00080 | $0.00080 |
| Haiku 4.5 | $0.00040 | $0.00040 |
Grade A, and why
prism-mem 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
AGENTS.md
Prism-mem is a knowledge graph generation system that extracts relations from coding sessions and stores them in a structured database.
Repository Layout
session_reader.py- Extracts sessionId from session filesgit_reader.py- Implements read_git_diff to extract code changesextractor.py- Calls Haiku API via LiteLLM to extract Graph.relationsmcp_server.py- Server component for agent interactionDesktop/Projects/prism-mem/- Project root location~/.claude/history.jsonl- Stores session transcripts~/.claude/projects/- Contains .jsonl files for session and subagent dataPrism-mem- Core knowledge graph storage system using SQLite with sqlite-vec extension
Build & Run
- Set
ANTHROPIC_API_KEYenvironment variable to authenticate with Anthropic API - Install dependencies including LiteLLM for Haiku model access and sqlite-vec extension
- Run extractor to process session files and generate Graph.relations
- Session data is automatically stored in
~/.claude/projects/as .jsonl files
Rules
- Always authenticate API calls using ANTHROPIC_API_KEY before accessing the Anthropic API
- Use similarity threshold for linking operations when connecting triples
- Call Haiku via LiteLLM (not direct API) for all extraction tasks
- Store all extracted Graph.relations in the knowledge graph via the kg-gen phase
- Subagents must write their own .jsonl files in
~/.claude/projects/with tool_result output - Phase 7 (constitution generator) scores all triples before final storage
- Parse JSON objects and extract the attachment field when processing session data
- Each session extracts relations through the extractor which calls create_edge() via link_triple
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 · 32 lines · 400 tokens per session scan A a901b534966a
prism-mem AGENTS.md is an instructions file published in the GitHub repository rahult18/prism-mem (2 stars, last pushed 3mo ago), licensed MIT. It adds 400 tokens to every session, about $0.0020 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
aeon CLAUDE.md
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.