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/coding-dev-tools/rtk-improved/agents-mdgit clone --depth 1 https://github.com/Coding-Dev-Tools/rtk-improvedWhat 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 | $0.00725 | $0.00725 |
| Opus 5 | $0.00362 | $0.00362 |
| Sonnet 5 | $0.00145 | $0.00145 |
| Haiku 4.5 | $0.00072 | $0.00072 |
Grade A, and why
rtk-improved 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RTK Token Optimization
RTK (Rust Token Killer) compresses shell command output before it enters the context window. Used well it cuts tokens on noisy commands and sharpens context (less noise → better reasoning). Used badly — compressing output you actually needed — it hides detail and forces re-runs that cost more than they save. These rules keep it net-positive.
Setup
RTK is optional. If rtk --version fails or rtk isn't on PATH, run commands
normally — never block work to install it.
The one rule: compress noise, preserve signal
Use rtk <cmd> when output is large, repetitive, low-stakes — skim, not
study: rtk ls, rtk git status, rtk git log, rtk docker ps,
rtk pip list, and big test/build runs (rtk cargo test, or rtk err <cmd> —
RTK keeps the failures and drops the green).
Run the command raw (no rtk) when you need every character:
- a diff/patch you'll apply, or a hunk you'll edit — exact bytes and line numbers matter
- structured output you'll parse — JSON,
--format=…, anything piped into another tool - small output (≲30 lines) — nothing to save, and real risk of dropping the one line you need
- secrets / exact config — never reason about a lossy view of these
- a file you intend to edit — use the native Read tool (lossless; it bypasses RTK anyway)
When unsure, start raw. Lean context comes from cutting noise, not signal.
Never default to lossy modes
Plain rtk <cmd> keeps the signal — errors, diffs, stack traces, exit codes —
and strips only noise. --ultra-compact, rtk read … -l aggressive, and
rtk smart (2-line summary) are lossy — opt-in only for skimming something
huge and unimportant, never your default. (RTK's own docs still mention a -u
short form for --ultra-compact; it was removed upstream and doesn't work — use
the long flag.)
Harness safety — don't let it break the tool call
- Don't wrap streaming/follow output (
-f,tail -f, a growing log): RTK buffers output to filter it, so it can hang the command. Run these raw. - When a pass/fail verdict matters (tests, CI gates), trust the command's raw
exit code. If you can't tell whether the
rtkview preserved it, re-run raw or usertk proxy <cmd>. - Prefer the native file/search tools over
rtk ls/grep/find/read— they're lossless, give line numbers, and don't pass through RTK anyway.
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 · 60 lines · 725 tokens per session scan A ba8c32257566
rtk-improved AGENTS.md is an instructions file published in the GitHub repository Coding-Dev-Tools/rtk-improved (10 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 725 tokens to every session, about $0.0036 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.