What is no-botshit CLAUDE.md?

A set of project instructions for maintaining the no-botshit Claude configuration and skill files. It defines the file layout, the source-of-truth skill file, and rules for documentation and benchmark changes.

Use it when changing the README, CLAUDE.md, or SKILL.md files, especially when updating installation guidance, benchmarks, or the project's deliberately blunt writing style.

It prevents duplicated instructions from drifting apart and keeps README claims, examples, token figures, and skill edits consistent with the project's stated rules.

no-botshit CLAUDE.md — Instructions file for coding agents by boutsioukis: A set of project instructions for maintaining the no-botshit…

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/boutsioukis/no-botshit/claude-md

Clone the repo

git clone --depth 1 https://github.com/boutsioukis/no-botshit

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/boutsioukis/no-botshit/claude-md.svg)](https://agentmods.dev/instructions/boutsioukis/no-botshit/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/boutsioukis/no-botshit/claude-md"><img src="https://agentmods.dev/badge/instructions/boutsioukis/no-botshit/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 662 This file is loaded in full into every session.

When invoked 662 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 5.1	$0.00662	$0.00662
Opus 5	$0.00331	$0.00331
Sonnet 5	$0.00132	$0.00132
Haiku 4.5	$0.00066	$0.00066

Measured 5d ago against content hash 093c0a878775, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

no-botshit CLAUDE.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 5d 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.

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.

CLAUDE.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — no-botshit

What this is

One skill. Two behaviors: council reasoning (internal) + caveman output (external).

Single source of truth: skills/no-botshit/SKILL.md. Root SKILL.md is a mirror — keep them in sync manually.

File layout

no-botshit/
├── README.md                  # Product pitch — most important file
├── SKILL.md                   # Root mirror (easy copy-paste for users)
├── CLAUDE.md                  # This file
├── CONTRIBUTING.md            # Contribution guide
├── LICENSE                    # MIT
├── install.sh                 # Bash installer shim
├── benchmarks/                # Real output-token harness (no committed results)
│   ├── run.py
│   ├── prompts.txt
│   └── README.md
└── skills/
    └── no-botshit/
        └── SKILL.md           # Source of truth — edit only here

Rules for README changes

Before/After examples stay first. That's the pitch.
Preserve caveman voice. "Big brain. Small mouth." is intentional.
Token math section must stay accurate. Don't invent numbers. The ~65% figure belongs to caveman's benchmark and must stay attributed to them — never restate it as ours. Our numbers come only from benchmarks/run.py.
Be honest that the council ADDS thinking tokens. no-botshit is not a universal token saver.
claude.ai needs Extended Thinking toggled on (model picker) for the council to stay out of the answer. ultrathink/effort: are Claude-Code-only. Keep install instructions in sync with this.
Install instructions must be tested before merge.
Paper citations must link to real papers and name the author (arXiv 2604.00025 = MD Azizul Hakim).

Rules for SKILL.md changes

Edit skills/no-botshit/SKILL.md — single source of truth.
Sync root SKILL.md after every change.
ultrathink keyword must stay — it triggers extended thinking for the council stages.
effort: high frontmatter must stay — council deliberation needs it.
Auto-clarity exception block must stay — safety before style.
Test: after changes, verify council stages still run silently (not echoed in output).

Read the full file on GitHub · 73 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.

5d ago First seen · 73 lines · 662 tokens per session scan A 093c0a878775

Subscribe to this mod's changes

no-botshit CLAUDE.md is an instructions file published in the GitHub repository boutsioukis/no-botshit (6 stars, last pushed 2mo ago), licensed MIT. It adds 662 tokens to every session, about $0.0033 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.

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

vscode buildNext.instructions.md

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

no-botshit CLAUDE.md