What is botskills CLAUDE.md?

A rulebook for AI agents working in the botskills.sh code repository. It explains the project, delegation rules, writing style, Git practices, and coding conventions.

Use it when editing, writing, committing, or delegating work in the botskills.sh repository.

It gives agents the repository-specific rules they need to follow, reducing inconsistent changes and accidental use of disallowed tools.

How PramodDutta/botskills configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to PramodDutta/botskills. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/PramodDutta/botskills/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/PramodDutta/botskills

Made for: Claude Code.

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/pramoddutta/botskills/claude-md/github.svg)](https://agentmods.dev/instructions/pramoddutta/botskills/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/pramoddutta/botskills/claude-md"><img src="https://agentmods.dev/badge/instructions/pramoddutta/botskills/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/pramoddutta/botskills/claude-md"><img src="https://agentmods.dev/badge/instructions/pramoddutta/botskills/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,634 This file is loaded in full into every session.

When invoked 1,634 The same file — it is already loaded in full.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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	$0.01634	$0.01634
Opus 5.5	$0.00654	$0.00654
Sonnet 5.5	$0.00327	$0.00327
Haiku 4.5	$0.00163	$0.00163

Measured 1mo ago against content hash 84a79a730b09, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

botskills CLAUDE.md scanned grade A with 1 finding 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 1mo 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.

Makes network callslowCapability

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

deployment URL, and a curl that proves the state). docs/ROLLBACK.md is the

CLAUDE.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Operating manual for AI agents in the botskills repo. Where a rule exists, follow it; do not improvise.

What this is

botskills.sh: directory of paste-ready bot skills for Grok Bot and Rakazo. Same architecture as qaskills.sh (see docs/PLAN.md and docs/SYSTEMS.md for the full plan, competitor research, and systems design). Separate repo, separate Vercel project, domain botskills.sh.

Delegation (STRICT, per Pramod 2026-08-23)

Use Fable (Claude) and Fable subagents ONLY in this repo. Never delegate to Codex CLI or Grok CLI here, even for bulk article generation. If subagent spawning is unavailable, Fable writes the content itself; do not fall back to other backends.

Conventions (inherited from qaskills, same strictness)

Writing: never use em dashes anywhere (chat, commits, docs, articles, code comments). Use comma, period, colon, parentheses, or "->". Grep for the character before finishing any writing deliverable.
Git: conventional commits, imperative mood, no Co-Authored-By trailers, no "Generated with Claude Code" footers. Stage explicit paths; review git diff --cached --stat before committing.
Code: Prettier style (single quotes, 2-space, 100 width), TypeScript strict. Server components fetch data; client components ('use client') own all interactivity; icons/functions never cross the boundary.
Do not bump @neondatabase/serverless to 1.x without upgrading drizzle-orm first. 1.0.0 removed the ability to call the query function as a plain function, and drizzle-orm 0.36.4 does exactly that (this.client(query, params, ...) in neon-http/session.cjs). The shim that supports both driver generations (this.clientQuery = client.query ?? client;) arrived in drizzle-orm 0.40.1. Order: drizzle to >= 0.40.1 first, verify, then the driver. This trap is silent. The peer range is >=0.10.0 and optional, so the install is clean, the build passes, and tsc passes; it fails only when a query runs. Check before trusting a green build: grep -c clientQuery packages/web/node_modules/drizzle-orm/neon-http/session.cjs must be non-zero. It is currently 0. Dormant today only because the drizzle db proxy in src/db/index.ts is not imported anywhere; all six live query sites use raw neon() tagged templates. It bites whoever first uses db.

Read the full file on GitHub · 117 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.

1mo ago Changed · +6 lines · +101 tokens per session 84a79a730b09
2mo ago Changed · +25 lines · +396 tokens per session 4fcbecaa9078
2mo ago First seen · 86 lines · 1,137 tokens per session scan A 798a23788566

Subscribe to this mod's changes

botskills CLAUDE.md is an instructions file published in the GitHub repository PramodDutta/botskills (24 stars, last pushed 1mo ago), licensed MIT. It adds 1,634 tokens to every session, about $0.0065 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

agent-skills ai-agents bot-directory grok-bot rakazo

botskills CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
botskills CLAUDE.mdPramodDutta/botskills	Instructions file	24	1mo ago	MIT	A	1,634	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

botskills: Instructions file for Claude Code