prism-mem AGENTS.md

prism-mem AGENTS.md is an instructions file for Codex, OpenCode from rahult18/prism-mem. It costs 400 tokens per session, scanned A, original, MIT.

Repository instructions for Prism-mem, a system that extracts relationships from coding sessions and stores them as a searchable knowledge graph in SQLite.

In plain words
What is it for?
Working on session reading, Git-diff extraction, relationship generation, MCP access, SQLite graph storage, and the project's build and authentication workflow.
Why use it?
They explain where session data comes from, how the graph is generated, and which authentication and linking rules the project requires.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/rahult18/prism-mem/agents-md
Clone the repo
git clone --depth 1 https://github.com/rahult18/prism-mem

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for prism-mem AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rahult18/prism-mem/agents-md.svg)](https://agentmods.dev/instructions/rahult18/prism-mem/agents-md)
Your own site
<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>
Per session 400 This file is loaded in full into every session.
When invoked 400 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 4d ago against content hash a901b534966a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

AGENTS.md · 32 lines

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 files
  • git_reader.py - Implements read_git_diff to extract code changes
  • extractor.py - Calls Haiku API via LiteLLM to extract Graph.relations
  • mcp_server.py - Server component for agent interaction
  • Desktop/Projects/prism-mem/ - Project root location
  • ~/.claude/history.jsonl - Stores session transcripts
  • ~/.claude/projects/ - Contains .jsonl files for session and subagent data
  • Prism-mem - Core knowledge graph storage system using SQLite with sqlite-vec extension

Build & Run

  1. Set ANTHROPIC_API_KEY environment variable to authenticate with Anthropic API
  2. Install dependencies including LiteLLM for Haiku model access and sqlite-vec extension
  3. Run extractor to process session files and generate Graph.relations
  4. Session data is automatically stored in ~/.claude/projects/ as .jsonl files

Rules

  1. Always authenticate API calls using ANTHROPIC_API_KEY before accessing the Anthropic API
  2. Use similarity threshold for linking operations when connecting triples
  3. Call Haiku via LiteLLM (not direct API) for all extraction tasks
  4. Store all extracted Graph.relations in the knowledge graph via the kg-gen phase
  5. Subagents must write their own .jsonl files in ~/.claude/projects/ with tool_result output
  6. Phase 7 (constitution generator) scores all triples before final storage
  7. Parse JSON objects and extract the attachment field when processing session data
  8. Each session extracts relations through the extractor which calls create_edge() via link_triple
Changes

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.

  1. 4d ago First seen · 32 lines · 400 tokens per session scan A a901b534966a

Subscribe to this mod's changes

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.