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/sukoji/loadout/browsenpx skills add sukoji/loadout --skill browsegit clone --depth 1 https://github.com/sukoji/loadoutWrote 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/sukoji/loadout/browse)<a href="https://agentmods.dev/skills/sukoji/loadout/browse"><img src="https://agentmods.dev/badge/skills/sukoji/loadout/browse.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 | $0.00043 | $0.00388 |
| Opus 5 | $0.00022 | $0.00194 |
| Sonnet 5 | $0.00009 | $0.00078 |
| Haiku 4.5 | $0.00004 | $0.00039 |
Grade A, and why
browse scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Loadout — browse the catalog
Read-only. Show what's in the catalog for a chosen domain; do not modify any files.
Steps
- Resolve the plugin root from
PLUGIN_ROOT,CLAUDE_PLUGIN_ROOT, or two levels above thisSKILL.md, then read itscatalog/domains.json,mcp.json,skills.json, andhooks.json. - If the user named a domain (or a stack that maps to one), use it. Otherwise list the domain
titles fromdomains.jsonand use the host's available user-input UI. If none is available, ask with a compact numbered list. - For the chosen domain, resolve its
loadoutids into the actual items and print them grouped by kind (MCP servers / Hooks & settings / Skills), each as name — description, with thehomepagelink and anyauth/notecaveat. - End by inviting the user to run Loadout's
recommendworkflow if they want these profiled against their repository and applied. When useful, identify the host-specific invocation ($recommendin Codex or/loadout:recommendin Claude Code). Note that catalog skill install commands are Claude-specific unless explicitly marked otherwise. Mention that token-saver skills (e.g. caveman) are not in browse; the recommendation workflow asks about those separately after the stack loadout.
Keep it scannable. This is the "read the shelf" mode; recommend is the "gear me up" mode.
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.
- 4d ago First seen · 27 lines · 43 tokens per session scan A 9ac1f08df601
browse is a skill published in the GitHub repository sukoji/loadout (2 stars, last pushed 4d ago), licensed MIT. It adds 43 tokens to every session and 388 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 2026-08-31.
Other skills, from other repositories
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
golden-rss
Use when testing the rss golden build.
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
apollo-lead-finder
Two-phase Apollo.io prospecting: free People Search to discover ICP-matching leads, then selective enrichment to reveal emails/phones (credits per contact). Creates Apollo lists. Deduplicates against existing contacts by LinkedIn URL.
google-ads-audit
Google Ads account audit and business context setup. Run this first — it gathers business information, analyzes account health, and saves context that all other ads skills reuse. Trigger on "audit my ads", "ads audit", "set up my ads", "onboard", "account overview", "how's my account", "ads health check", "what should…
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.