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/rajitsaha/100xprism/agents-mdgit clone --depth 1 https://github.com/rajitsaha/100xprismWrote 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/rajitsaha/100xprism/agents-md)<a href="https://agentmods.dev/instructions/rajitsaha/100xprism/agents-md"><img src="https://agentmods.dev/badge/instructions/rajitsaha/100xprism/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 | $0.01692 | $0.01692 |
| Opus 5 | $0.00846 | $0.00846 |
| Sonnet 5 | $0.00338 | $0.00338 |
| Haiku 4.5 | $0.00169 | $0.00169 |
Grade A, and why
100xprism 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 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Contributor contract for AI coding agents working on this repo. Users see README.md and docs/USAGE.md; this file is for agents editing the repo itself.
What this repo is
100xprism is a distributor, not an app. The product is modules/ (68 SKILL.md files with YAML frontmatter). Adapters in adapters/ render those modules into each AI tool's native format: Claude Code skills, Cursor .mdc, Codex repo skills + AGENTS.md, a Pi package (retention-filtered .pi/skills/ + extensions), and Hermes/OpenClaw global skills. Users install via npm i -g 100xprism or get.sh. For Pi: pi install git:github.com/rajitsaha/100xprism.
Every adapter uses progressive disclosure — descriptions in the always-on index, bodies loaded on demand. The single-file concat adapters (Windsurf/Copilot/Gemini/Antigravity) were removed in v3.0.0 precisely because they could not do this.
The golden rule
A module is the source of truth. Adapter output is generated. Edit modules/<slug>/SKILL.md. Never hand-edit ~/.claude/skills/*, .cursor/rules/*.mdc, .pi/skills/*, or any rendered artifact in a consumer project — those are reset by the next adapter run.
Module shape
Each module is one file: modules/<slug>/SKILL.md with frontmatter:
---
name: <slug>
description: <one-line trigger guidance — used by Claude Code/Cursor for auto-activation>
category: <docs|code|growth|...>
tier: <core|on-demand>
slash_command: /<name> # optional — only for the 28 command-style modules
retention: <must|profile|resolver> # optional — overrides the derived class
profiles: <core, code, data, …> # optional — overrides the category default
---
A module must work across all 5 adapters. If you add tool-specific instructions, gate them inside the module body, not the frontmatter. Hermes has one extra constraint the others don't: its always-on index truncates description: past ~57 chars, so adapters/lib/modules.py's hermes_description() re-derives a short one for that adapter only (override per-module with hermes_description: in frontmatter if the derived cut reads awkwardly) — the source module's description: is unaffected.
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 · 107 lines · 1,692 tokens per session scan A 99104021639b
100xprism AGENTS.md is an instructions file published in the GitHub repository rajitsaha/100xprism (10 stars, last pushed 4d ago), licensed MIT. It adds 1,692 tokens to every session, about $0.0085 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 2026-09-03.
Other instructions, from other repositories
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).
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.