Borrowing it
Nothing to install: this file belongs to softspark/ai-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/softspark/ai-toolkit/main/AGENTS.mdgit clone --depth 1 https://github.com/softspark/ai-toolkitWrote 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/softspark/ai-toolkit/agents-md)<a href="https://agentmods.dev/instructions/softspark/ai-toolkit/agents-md"><img src="https://agentmods.dev/badge/instructions/softspark/ai-toolkit/agents-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.
<a href="https://agentmods.dev/instructions/softspark/ai-toolkit/agents-md"><img src="https://agentmods.dev/badge/instructions/softspark/ai-toolkit/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02370 | $0.02370 |
| Opus 5.5 | $0.00948 | $0.00948 |
| Sonnet 5.5 | $0.00474 | $0.00474 |
| Haiku 4.5 | $0.00237 | $0.00237 |
Grade B, and why
ai-toolkit AGENTS.md scanned grade B 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 6d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
# Install: ai-toolkit install (global → ~/.claude/settings.json hooks + ~/.softspark/ai-toolkit/hooks/ scripts) How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ai-toolkit
Overview
Shared AI development toolkit for Claude Code, Claude Chat/Cowork, and 11 editor integrations. It distributes skills, agents, lifecycle hooks, persona presets, plugin packaging, and the safety constitution as a global npm package.
Agent Runtime Rules
- This file is the repository's instructions for every coding agent. Codex, Copilot, OpenCode, Gemini CLI and Antigravity read it natively; Claude Code reads it through the
@AGENTS.mdimport inCLAUDE.md(since v2.1.277 Claude readsAGENTS.mdon its own only when noCLAUDE.mdexists in the working directory or above it, code.claude.com/docs/en/memory). Keep it under 24,000 bytes: Antigravity truncates larger rule files. - Claude Code also reads
.claude/CLAUDE.md,.claude/rules/*.md, skills, agents, settings, and hooks; put Claude-only instructions inCLAUDE.mdbelow the import. - Claude Chat/Desktop/Cowork does not scan Claude Code's
~/.claude/files. Useai-toolkit claude-app export, upload the ZIP in Customize > Plugins, and apply the generated Cowork global instructions. Skills work in Chat/Cowork; hooks and sub-agents are Cowork-only. - KB-first is mandatory for technical work: before answering or acting on a technical/project prompt, call
smart_query()orhybrid_search_kb()and use the result to locate the relevant SOP/reference. Cite the KB path when the result materially informs the answer. If the KB tool is unavailable, state that explicitly and continue from local files. - Any rule that must be enforced at a fixed lifecycle point belongs in
app/hooks.json+app/hooks/*.shwith tests. Instruction files are context, not enforcement.
CRITICAL: Documentation & Count Accuracy
Every change to skills, agents, hooks, or editors MUST be reflected in ALL docs:
README.md, AGENTS.md, ARCHITECTURE.md, package.json, plugin.json, skills-catalog.md, architecture-overview.md, llms.txt.
Run python3 scripts/validate.py --strict + python3 scripts/audit_skills.py --ci before every commit.
When you touch any app/hooks/*.sh, ALSO run shellcheck --severity=warning app/hooks/*.sh — it is NOT part of validate.py or npm test. No GitHub workflow runs tests or lint: CI only publishes a tag, and every gate (ShellCheck included) runs locally in npm run release -- X.Y.Z (scripts/release.sh, see kb/procedures/sop-release.md).
Stale counts = broken user trust. This is non-negotiable.
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.
- 6d ago Changed · -1 lines · -109 tokens per session 8667ced4a62d
- 8d ago First seen · 92 lines · 2,479 tokens per session scan B e560a0cc06d5
ai-toolkit AGENTS.md is an instructions file published in the GitHub repository softspark/ai-toolkit (180 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,370 tokens to every session, about $0.0095 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-09.
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).
next.js AGENTS.md
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, cache eligibility and rollout and applying the notice (cutover).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).