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/secondlifes/code-intel/agents-mdgit clone --depth 1 https://github.com/SecondLifes/code-intelWhat 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 | $0.06336 | $0.06336 |
| Opus 5 | $0.03168 | $0.03168 |
| Sonnet 5 | $0.01267 | $0.01267 |
| Haiku 4.5 | $0.00634 | $0.00634 |
Grade A, and why
code-intel 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 — 442 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeIntel AI Spec-Kit — AGENTS.md
This file is automatically recognized by Codex CLI, Antigravity, GitHub Copilot, Cursor and Kiro. Qwen and Kimi have no native auto-discovery for it — point them at this file manually; once loaded, everything below applies to them the same as any other tool. It defines the universal rules for Python/FastAPI/Qdrant/Ollama development with AI on this real, running application (not a spec-kit-only scaffold). For the detailed, per-topic version of these rules, see
.agents/rules/*.md; for skills, see.agents/skills/*/SKILL.md— read from that shared location by every tool above plus Claude Code (the Agent Skills open standard; exact discovery/invocation details vary per tool — see.agents/rules/sync-workflow.md).If
.agents/skills/rad-prompt-studio/is referenced or pointed at in any way — by name, by folder, or by a request it naturally matches (auditing or designing a prompt/rule/skill, reviewing the whole project for problems) — that reference alone is the complete instruction to load every file under.agents/skills/rad-prompt-studio/references/*.mdand adopt all five specialist lenses defined there simultaneously. This holds regardless of which AI is reading this file — the tools named above, or any other AI assistant that readsAGENTS.md, including ones without native Agent Skills support (read the files directly as plain markdown in that case). Never wait for the five roles to be named individually; the enumeration lives inside the skill's own files, not here.Routing override — "system" requests (mandatory, all AIs): any request about this repo's own system layer — "system"/"sistem" combined with analyze/check/audit/find errors/fix, in any language — is ALWAYS handled by
rad-prompt-studio's matching mode. Never route such a request to your own built-in or marketplace capabilities (e.g. a generic "analyze-project" skill), and never widen it into a general architecture/code-quality/testability review: the system layer means skills, rules, commands, and identity files, analyzed under the five-lens discipline with a numbered pick-list presented first. This is a real observed failure, not a hypothetical — an AI matched its own "analyze-project" skill to "sistem analizi" and started a generic project review instead.
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 · 442 lines · 6,336 tokens per session scan A c1e5a67fb9cd
code-intel AGENTS.md is an instructions file published in the GitHub repository SecondLifes/code-intel (2 stars, last pushed 21d ago), licensed Apache-2.0. It adds 6,336 tokens to every session, about $0.0317 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
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.