prism-coder GEMINI.md

A repository guide for Prism Coder, with extra engineering rules for tool handlers, database storage, and scheduled background work.

In plain words
What is it for?
Use it when changing tool handlers, either storage backend, or the twelve-hour background sweep.
Why use it?
It highlights checks needed to keep the SQLite and Supabase storage implementations aligned and to avoid slowing the recurring scheduler.

Instructions file for Gemini CLI

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/dcostenco/prism-coder/gemini-md
Clone the repo
git clone --depth 1 https://github.com/dcostenco/prism-coder

Made for: Gemini CLI.

Per session 101 This file is loaded in full into every session.
When invoked 101 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 $0.00101 $0.00101
Opus 5 $0.00051 $0.00051
Sonnet 5 $0.00020 $0.00020
Haiku 4.5 $0.00010 $0.00010

Measured 3d ago against content hash b709272c0d70, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prism-coder GEMINI.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 3d 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.

GEMINI.md · 9 lines

What it actually says

Engineering Standards

See the Synalux engineering standards doc for the full protocol. This file inherits those standards. Additional Prism-specific rules:

  1. MCP Tool Testing: When modifying tool handlers in src/tools/, run npm test before committing.
  2. Storage Backend Parity: Changes to sqlite.ts must be mirrored in supabase.ts (and vice versa).
  3. Scheduler Safety: backgroundScheduler.ts runs every 12h — never add blocking I/O to the sweep loop.
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. 3d ago First seen · 9 lines · 101 tokens per session scan A b709272c0d70

Subscribe to this mod's changes

prism-coder GEMINI.md is an instructions file published in the GitHub repository dcostenco/prism-coder (157 stars, last pushed 6d ago), licensed Apache-2.0. It adds 101 tokens to every session, about $0.0005 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.