What is prism AGENTS.md?

A set of instructions for AI coding agents working on the Prism software project, a local tool for understanding software repositories. It defines the project's source documents, development rules, and branch conventions.

Use it when planning, implementing, checking, branching, merging, or documenting work in the Prism repository.

It helps agents follow the project's required order of work and avoid unapproved commits, merges, pushes, or changes on the main branch.

prism AGENTS.md — Instructions file by Shailesh200

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/shailesh200/prism/agents-md

Clone the repo

git clone --depth 1 https://github.com/Shailesh200/prism

Made for: Codex, OpenCode.

Per session 544 This file is loaded in full into every session.

When invoked 544 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.

Model	Per session	Once invoked
Fable 5	$0.00544	$0.00544
Opus 5	$0.00272	$0.00272
Sonnet 5	$0.00109	$0.00109
Haiku 4.5	$0.00054	$0.00054

Measured 2d ago against content hash b23e15fe3689, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

prism 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 2d 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 · 59 lines

How it starts

The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Working on Prism

This repository is Prism, a local-first Software Intelligence Engine (formerly working name RepoPulse).

Source of truth

plans/00_MASTER_DEVELOPMENT_PLAN.md
Active milestone doc under plans/milestones/
plans/PROGRESS.md

If code and plan disagree, stop and reconcile the plan before continuing.

Hard Rules (mandatory)

Never implement product code before the Master Plan is approved and M-000 (architecture docs) is Verified.
Never create git commits until the owner explicitly approves (e.g. “approve”, “commit”, “approve M-XXX”). Keep changes uncommitted until then.
One active milestone at a time.
One milestone = one Git branch.
Never develop on main.
Never stack milestone branches.
Never merge without owner approval.
Never push unless owner explicitly asks.
Every milestone must pass the complete verification suite.
Every merge to main must leave the repository buildable.
Every milestone must update the Master Plan progress.
After a milestone is committed and merged to main, always share a short snippet with the owner of what changed (bullets: APIs, packages, ADRs/plan notes). Keep it brief.

Architecture rules

All user-facing surfaces consume @repo-prism/core for analysis. The MCP server may also import @repo-prism/dispatch for jobs/OAuth (ADR-0035). The website may import @repo-prism/dispatch-auth for the OAuth broker (ADR-0036). Do not put Dispatch inside Core.
Do not reimplement analysis inside extensions or MCP tools.
Prefer smaller milestones; do not expand scope without owner approval.
New architectural choices require an ADR in plans/adr/.
Privacy default: no network calls for core analysis.

Branch convention

milestone/M-XXX-short-name

Verification

bun run verify:milestone

What Prism is / is not

Is: repository intelligence, maps, graphs, impact analysis, MCP tools for agents
Is not: an AI coding assistant / LLM product

Read the full file on GitHub · 59 lines

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.

2d ago First seen · 59 lines · 544 tokens per session scan A b23e15fe3689

Subscribe to this mod's changes

prism AGENTS.md is an instructions file published in the GitHub repository Shailesh200/prism (1 stars, last pushed 2d ago), licensed MIT. It adds 544 tokens to every session, about $0.0027 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.

Git and workflow Planning

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

prism AGENTS.md