Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/ulises-jeremias/agent-toolkitnpx agentmods add skills/ulises-jeremias/agent-toolkit/inventoryWrote 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/ulises-jeremias/agent-toolkit/inventory)<a href="https://agentmods.dev/skills/ulises-jeremias/agent-toolkit/inventory"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/inventory/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/skills/ulises-jeremias/agent-toolkit/inventory"><img src="https://agentmods.dev/badge/skills/ulises-jeremias/agent-toolkit/inventory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.00807 |
| Opus 5.5 | $0.00010 | $0.00323 |
| Sonnet 5.5 | $0.00005 | $0.00161 |
| Haiku 4.5 | $0.00003 | $0.00081 |
Grade A, and why
inventory 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 yesterday.
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.
Inventory
Discover what the toolkit can do before you build — skills, agents, loops, MCP, and platform support — via agent-toolkit inventory, matrix, build --check, and skills list.
When to use
- User asks "what can agent-toolkit do?", "what skills are available?", or "is there a skill for X".
- Before starting delivery: check which workflow (
delivery/*), forge (github-cli-workflow), or ops (swarm) skills apply. - After
agent-toolkit install— verify what was deployed and what needsmcp setup. - Before running
buildorplugin— understand target support viamatrix.
Workflow
1. List everything
agent-toolkit inventory # skills (61), agents (16), loops (10), products
agent-toolkit matrix # platform capability matrix (claude-code, cursor, opencode, etc.)
agent-toolkit skills list # grouped by domain (core, ops, forge, etc.)
agent-toolkit skills list --domain ops # filter
agent-toolkit loops --help 2>&1 | head
inventory now shows 61 skills across 9 domains including the new swarm family:
ops/swarm,ops/swarm-observer,ops/swarm-handoff,tooling/herdr,forge/worktree,core/workspace,core/project,integrations/mcp,tooling/inventory.
2. Inspect a skill or agent
agent-toolkit skills validate # all 61 should be ✓
muse skills validate ~/.ai-workspace/.agents/skills/swarm --json | jq .valid
cat skills/ops/swarm/SKILL.md | head -n 20
cat agents/code-reviewer/AGENT.md | head -n 20
ls plugins/ # agent-toolkit-core, agent-toolkit-forge, etc. — each maps skills+agents to targets
3. Check readiness before delivery
agent-toolkit doctor
agent-toolkit mcp doctor
agent-toolkit swarm doctor # herdr/tmux + runner model profiles
agent-toolkit build --check # validate compilation without writing plugins/
4. After adding skills (host vs checkout)
Host / installed toolkit (consumers): use the CLI only — do not expect repo-root scripts/ (it is not installed to XDG/wheel):
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.
- yesterday Changed 3acf744dbe79
- 1mo ago First seen · 86 lines · 25 tokens per session scan A f7843a134529
inventory is a skill published in the GitHub repository ulises-jeremias/agent-toolkit (19 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 807 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-04.
Other skills, from other repositories
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.
skillnote
Self-hosted skill registry for OpenClaw. Stores procedures your team writes (name, description, body), syncs them to disk before each task, and collects which-helped/which-failed signals from the agent so the registry improves over time.
pr-alignment-loop
Iterate a PR to its final form by running two opposing reviewer droids (reviewer-robustness and reviewer-minimalist) in a bounded back-and-forth loop. The main orchestrator synthesizes their feedback, makes edits, runs tests, and stops when both approve, on stagnation, or after 3 rounds. Use when the user asks to…
publish-website
Publish a website to Porkbun Secure Static Hosting. Use when the user asks you to build, create, update or put live a website, landing page or placeholder page for a domain they have at Porkbun, mentions Porkbun hosting or static hosting, or asks how to upload site files to Porkbun.
create-rule
Use when creating, writing, or updating a Claude Code rule file (.claude/rules/.md or /.claude/rules/.md), or when asking about rule format, path scoping, or rule best practices.
platform-setup
Set up, verify, and troubleshoot Katalon True Platform/TestOps MCP connectivity for any AI coding agent. Use when you need to install or configure the Katalon MCP server, connect to a Katalon platform account, verify available Katalon MCP tools, diagnose missing authentication or repository access, confirm…