What is code-intel-platform copilot-instructions.md?

A set of instructions for using RTK, a command-line wrapper that filters and shortens command output, and code-intel, a tool for searching and understanding code.

Use it when working on the code-intel-platform project to run shell commands, inspect code, trace affected callers, and review token savings.

It helps reduce the amount of terminal output an agent must read and directs code exploration through the project's required tools.

code-intel-platform copilot-instructions.md — Instructions file by vohongtho

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/vohongtho/code-intel-platform/copilot-instructions

Clone the repo

git clone --depth 1 https://github.com/vohongtho/code-intel-platform

Made for: GitHub Copilot.

Per session 2,807 This file is loaded in full into every session.

When invoked 2,807 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	$0.02807	$0.02807
Opus 5	$0.01404	$0.01404
Sonnet 5	$0.00561	$0.00561
Haiku 4.5	$0.00281	$0.00281

Measured yesterday against content hash c3df4429d833, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-intel-platform 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.

.github/copilot-instructions.md · 207 lines

How it starts

The opening of the file, as written. The whole thing — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.

RTK — Token-Optimized CLI

rtk is a CLI proxy that filters and compresses command outputs, saving 60-90% tokens.

Rule

Always prefix shell commands with rtk:

# Instead of:              Use:
git status                 rtk git status
git log -10                rtk git log -10
cargo test                 rtk cargo test
docker ps                  rtk docker ps
kubectl get pods           rtk kubectl pods

Meta commands (use directly)

rtk gain              # Token savings dashboard
rtk gain --history    # Per-command savings history
rtk discover          # Find missed rtk opportunities
rtk proxy <cmd>       # Run raw (no filtering) but track usage

Code Intelligence — code-intel-platform

⚠ This section is auto-managed by code-intel analyze. Do not edit between the markers — your changes will be overwritten. Add your own notes below the  marker.

FORBIDDEN: grep, rg, find, cat, sed, ls (for symbol/code discovery) REQUIRED BEFORE ANY CODE ACTION:

code-intel search "" ← replaces grep/rg/find
code-intel inspect ← replaces cat + manual file reading
code-intel impact ← replaces manual caller tracing

Indexed: 6,278 nodes | 11,417 edges | 333 files | analyzed in 1.3s

Index stale? Re-run: code-intel analyze

Mandatory Rules — ALL Agents (Amp, Claude Code, Codex, Copilot, Cursor, Aider, Gemini, Kiro, Trae, Hermes, Factory, OpenCode, Pi, Antigravity, OpenClaw, and others)

These rules apply to every coding agent or AI assistant working in this repository.

Before Implementing Any Change

Run code-intel search "<concept>" — find existing symbols related to the task.
Run code-intel inspect <symbol> — understand callers, callees, and imports.
Run code-intel impact <symbol> — check blast radius before touching anything.
If impact shows ≥ 5 direct callers → warn the user: HIGH risk.

Read the full file on GitHub · 207 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.

yesterday First seen · 207 lines · 2,807 tokens per session scan A c3df4429d833

Subscribe to this mod's changes

code-intel-platform copilot-instructions.md is an instructions file published in the GitHub repository vohongtho/code-intel-platform (3 stars, last pushed 6d ago), licensed MIT. It adds 2,807 tokens to every session, about $0.0140 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.

Code review Research

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

code-intel-platform copilot-instructions.md