grit CLAUDE.md

grit CLAUDE.md is an instructions file for coding agents from rtk-ai/grit. It costs 1,479 tokens per session, scanned C, original, Apache-2.0.

A set of instructions for an AI coding agent that uses persistent memory between work sessions and shorter command output. It explains when to recall or save project knowledge and how to prefix commands with RTK.

In plain words
What is it for?
Use it to search, save, update, and audit project memories, record corrections, and run shell commands through RTK.
Why use it?
It helps the agent retain important decisions and lessons instead of starting from scratch each session. RTK can reduce command output where supported, making responses use fewer tokens.

Instructions file

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/rtk-ai/grit/claude-md
Clone the repo
git clone --depth 1 https://github.com/rtk-ai/grit

Wrote 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.

agentmods badge for grit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rtk-ai/grit/claude-md.svg)](https://agentmods.dev/instructions/rtk-ai/grit/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/rtk-ai/grit/claude-md"><img src="https://agentmods.dev/badge/instructions/rtk-ai/grit/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,479 This file is loaded in full into every session.
When invoked 1,479 The same file — it is already loaded in full.
Security scan C 2 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.

ModelPer sessionOnce invoked
Fable 5 $0.01479 $0.01479
Opus 5 $0.00740 $0.00740
Sonnet 5 $0.00296 $0.00296
Haiku 4.5 $0.00148 $0.00148

Measured 4d ago against content hash e513f2f7b075, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

grit CLAUDE.md scanned grade C with 2 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 4d ago.

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.

Hidden instructionshighPrompt injection

Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.

<!-- rtk-instructions v2 -->

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

rtk curl <url> # Compact HTTP responses (70%)
Origin

Copies of this mod

5 near-identical copies found in the catalogue:

CLAUDE.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Persistent memory (ICM)

This project uses ICM for persistent memory across sessions.

Recall (before starting work)

icm recall "topic keywords"              # search memories
icm recall-context "query" --limit 5     # formatted for prompt injection

Store (after completing significant work)

icm store -t "topic" -c "summary" -i medium   # importance: critical|high|medium|low
icm store -t "decisions" -c "chose X over Y because..." -i high
icm store -t "errors-resolved" -c "fix: ..." -k "error,fix"

Other commands

icm update <id> -c "updated content"     # edit memory in-place
icm health                                # topic hygiene audit
icm topics                                # list all topics
icm feedback record -t "topic" -c "context" -p "predicted" --corrected "actual"

RTK (Rust Token Killer) - Token-Optimized Commands

Golden Rule

Always prefix commands with rtk. If RTK has a dedicated filter, it uses it. If not, it passes through unchanged. This means RTK is always safe to use.

Important: Even in command chains with &&, use rtk:

# ❌ Wrong
git add . && git commit -m "msg" && git push

# ✅ Correct
rtk git add . && rtk git commit -m "msg" && rtk git push

RTK Commands by Workflow

Build & Compile (80-90% savings)

rtk cargo build         # Cargo build output
rtk cargo check         # Cargo check output
rtk cargo clippy        # Clippy warnings grouped by file (80%)
rtk tsc                 # TypeScript errors grouped by file/code (83%)
rtk lint                # ESLint/Biome violations grouped (84%)
rtk prettier --check    # Files needing format only (70%)
rtk next build          # Next.js build with route metrics (87%)

Test (90-99% savings)

rtk cargo test          # Cargo test failures only (90%)
rtk vitest run          # Vitest failures only (99.5%)
rtk playwright test     # Playwright failures only (94%)
rtk test <cmd>          # Generic test wrapper - failures only

Read the full file on GitHub · 160 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.

  1. 4d ago First seen · 160 lines · 1,479 tokens per session scan C e513f2f7b075

Subscribe to this mod's changes

grit CLAUDE.md is an instructions file published in the GitHub repository rtk-ai/grit (114 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 1,479 tokens to every session, about $0.0074 per session on Opus 5. A static security scan graded it C with 2 findings (hidden instructions, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.