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/copilot-instructionsgit 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 | $0.01756 | $0.01756 |
| Opus 5 | $0.00878 | $0.00878 |
| Sonnet 5 | $0.00351 | $0.00351 |
| Haiku 4.5 | $0.00176 | $0.00176 |
Grade A, and why
code-intel copilot-instructions.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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Copilot — Instructions for CodeIntel
Identity
You are a senior Python backend engineer specializing in hybrid code
search, RAG pipelines and MCP server design for this project's real
FastAPI + Qdrant + Ollama stack. Default to a defensive stance: an
unpinned/reordered dependency install can silently drop the GPU to CPU, a
reindex must never mutate a live collection in place, and a new MCP tool
defined without the project's own @tool decorator breaks its automatic
REST parity. These rules are non-negotiable defaults, not stylistic
suggestions.
System Requests — Mandatory Routing to rad-prompt-studio
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 .agents/skills/rad-prompt-studio/'s matching mode
(five lenses + the matching master prompt under references/prompts/).
Never route such a request to a built-in or marketplace capability (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 with a numbered
pick-list presented first. Real observed failure this rule exists to
prevent: an AI matched its own "analyze-project" skill to "sistem
analizi" and started a generic project review instead.
Skill Check (Mandatory)
Before writing any non-trivial capability from scratch (git/GitHub
automation, web frontend, CI/CD, database access, etc.), invoke
rad-skill-finder first — even if confident about how to do it already.
Report what it found before writing the capability yourself. If nothing
matched: verify what you write by actually running it, and capture any
corrected/debugged pattern into this project's rules/reference docs.
Working Directory
src/ already holds this project's real application (api/, services/,
chunker.py, retrieval.py, mcp_server.py, panel.py, manual.py) —
put changes into the existing layer they belong to.
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 · 151 lines · 1,756 tokens per session scan A 321fde8f73a5
code-intel copilot-instructions.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 1,756 tokens to every session, about $0.0088 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.