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/pramoddutta/botskills/claude-mdgit clone --depth 1 https://github.com/PramodDutta/botskillsWrote 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.
[](https://agentmods.dev/instructions/pramoddutta/botskills/claude-md)<a href="https://agentmods.dev/instructions/pramoddutta/botskills/claude-md"><img src="https://agentmods.dev/badge/instructions/pramoddutta/botskills/claude-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01137 | $0.01137 |
| Opus 5 | $0.00568 | $0.00568 |
| Sonnet 5 | $0.00227 | $0.00227 |
| Haiku 4.5 | $0.00114 | $0.00114 |
Grade A, and why
botskills 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 86 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 --statbefore 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/serverlessto 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, ...)inneon-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>=0.10.0and optional, so the install is clean, the build passes, andtscpasses; 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.cjsmust be non-zero. It is currently 0. Dormant today only because the drizzledbproxy insrc/db/index.tsis not imported anywhere; all six live query sites use rawneon()tagged templates. It bites whoever first usesdb.
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.
- 3d ago First seen · 86 lines · 1,137 tokens per session scan A 798a23788566
botskills CLAUDE.md is an instructions file published in the GitHub repository PramodDutta/botskills (2 stars, last pushed 4d ago), licensed MIT. It adds 1,137 tokens to every session, about $0.0057 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
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).
spec-kit AGENTS.md
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.
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.
langchain AGENTS.md
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.
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).
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.