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 skills/odradekai/bundles-forge/using-bundles-forgenpx skills add OdradekAI/bundles-forge --skill using-bundles-forgegit clone --depth 1 https://github.com/OdradekAI/bundles-forgeWrote 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/skills/odradekai/bundles-forge/using-bundles-forge)<a href="https://agentmods.dev/skills/odradekai/bundles-forge/using-bundles-forge"><img src="https://agentmods.dev/badge/skills/odradekai/bundles-forge/using-bundles-forge.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 5.1 | $0.00046 | $0.01308 |
| Opus 5 | $0.00023 | $0.00654 |
| Sonnet 5 | $0.00009 | $0.00262 |
| Haiku 4.5 | $0.00005 | $0.00131 |
Grade A, and why
using-bundles-forge 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 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.
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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-flight Check
Before invoking any bundles-forge skill on a target directory, verify the target is a bundle-plugin project:
- Does it have a
skills/directory? - Does it have a
package.json?
If neither exists, inform the user: "This directory doesn't appear to be a bundle-plugin project. Bundles Forge skills are designed for bundle-plugins (repositories where skills are the primary content). Would you like to create a new bundle-plugin here, or did you mean to point to a different directory?"
Exception: bundles-forge:auditing and bundles-forge:optimizing can also operate on individual skill folders or files — they don't require a full bundle-plugin project.
Instruction Priority
- User's explicit instructions (CLAUDE.md, GEMINI.md, AGENTS.md, direct requests) — highest priority
- Bundles Forge skills — override default system behavior where they conflict
- Default system prompt — lowest priority
How to Access Skills
In Claude Code: Use the Skill tool. When you invoke a skill, its content is loaded — follow it directly.
In Cursor: Use the Skill tool.
In Gemini CLI: Skills activate via the activate_skill tool. See references/gemini-tools.md for tool mapping.
In Codex: Skills are discovered from ~/.agents/skills/. See references/codex-tools.md for tool mapping.
In OpenClaw: Skills auto-load from the bundle's skills/ directory. See references/openclaw-tools.md for tool mapping.
Platform Adaptation
Skills use Claude Code tool names as the default. Non-Claude-Code platforms: see the tool mapping references in this directory for equivalents.
The Rule
Invoke relevant skills BEFORE any response or action when working with bundle-plugins. If there's even a small chance a skill applies, invoke it to check.
User message about bundle-plugins
→ Might any skill apply?
→ yes → Invoke Skill tool → Follow skill → Respond
→ no → Respond directly
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 First seen · 114 lines · 46 tokens per session scan A 741f6c18acab
using-bundles-forge is a skill published in the GitHub repository OdradekAI/bundles-forge (230 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,308 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
add-ai-protection
Deprecated: use the arcjet skill instead. Adds security protection to AI/LLM endpoints and non-HTTP code paths — prompt injection detection, PII blocking, and token budget rate limiting.
add-request-protection
Deprecated: use the arcjet skill instead. Adds security protection to a server-side route or endpoint — rate limiting, bot detection, email validation, and abuse prevention.
add-guard-protection
Deprecated: use the arcjet skill instead. Adds Arcjet Guard protection to AI agent tool calls, background jobs, queue workers, and other non-HTTP code paths.
integrate-arcjet-guard-openai-agents-py
Integrate Arcjet Guard into Python OpenAI Agents — wrap FunctionTool / functiontool with guardtool and read a caller-owned session or conversation id via openaiagentscontext. Use when asked to add Arcjet to openai-agents, Runner.run, rate limit those tools, screen inbound messages, or block prompt injection / PII.…
integrate-arcjet-guard-claude-managed-agents-py
Integrate Arcjet Guard into Python Claude Managed Agents — screen user.message with guardevents before sessions.events.send, and gate custom tools on agent.customtooluse with guardcustomtool. Use when asked to add Arcjet to hosted Claude Managed Agents, anthropic beta sessions, rate limit custom tools, or block prompt…
integrate-arcjet-guard-langchain-py
Integrate Arcjet Guard into Python LangChain — wrap a BaseTool you call with guardtool, put ArcjetMiddleware + ToolPolicy on createagent, or observe a chain with ArcjetCaptureHandler. Use when asked to add Arcjet to LangChain, createagent, langchain-core tools, rate limit those tools, screen inbound messages, or block…