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/jcottam/agent-resources/hostnpx skills add jcottam/agent-resources --skill hostgit clone --depth 1 https://github.com/jcottam/agent-resourcesWhat 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 | $0.00113 | $0.01282 |
| Opus 5 | $0.00056 | $0.00641 |
| Sonnet 5 | $0.00023 | $0.00256 |
| Haiku 4.5 | $0.00011 | $0.00128 |
Grade A, and why
host 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 2d 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 — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Host
Upload any file to Cloudflare R2 and get back a shareable public URL.
SCRIPTS below refers to the scripts/ directory next to this file.
Prerequisites
- Wrangler CLI — the Cloudflare developer CLI used for all R2 operations
- Cloudflare account with an R2 bucket that has public access enabled (r2.dev subdomain or custom domain)
- Wrangler authenticated via one of:
wrangler login(interactive OAuth — run once, token persists in~/.wrangler)CLOUDFLARE_API_TOKENenvironment variable
Step 1 — Check prerequisites
Wrangler installation
Check if wrangler is available:
wrangler --version
If not installed, install it globally:
npm install -g wrangler
Wrangler authentication
Verify auth status:
wrangler whoami
If not authenticated, the user must run wrangler login interactively (opens a browser for OAuth). This is a one-time step.
Host configuration
Look for ~/.publish.json. If it doesn't exist, run $SCRIPTS/setup.sh and walk the user through the prompts. The setup script creates the config file with:
{
"bucket": "my-bucket-name",
"publicBaseUrl": "https://pub-xxx.r2.dev"
}
If the file exists, read it and parse the bucket and publicBaseUrl values. Both are required.
Step 2 — Identify the asset
Determine what file to host from context:
- If the user specified a file path, use that.
- If the user said "host this" without a path, check for:
- A file the user is currently viewing or recently created
- A
.canvas.tsxoutput or generated HTML file from the current session
- Verify the file exists before proceeding. If ambiguous, ask the user to clarify.
Step 3 — Generate the key
Decide the R2 object key (the path within the bucket):
- Default: derive a readable slug from the filename.
- Strip extension, lowercase, replace spaces and special characters with hyphens
- Append today's date:
my-report-2026-05-15 - Re-attach the original file extension
- Example:
Sales Report Q1.htmlbecomessales-report-q1-2026-05-15.html
- User override: if the user provided a custom name, use it instead (sanitized).
- Collision check: scan
~/.publish-history.jsonfor the key. If it exists, ask the user whether to overwrite or append a suffix (-2,-3, etc.).
What ships with it
4 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.
- 2d ago First seen · 147 lines · 113 tokens per session scan A 823449344f76
host is a skill published in the GitHub repository jcottam/agent-resources (30 stars, last pushed 26d ago), licensed MIT. It adds 113 tokens to every session and 1,282 once invoked, about $0.0006 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
workers-best-practices
Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from…
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
story-origin-check
Recover the first public timestamp and canonical major coverage for a newsjacking signal, then decide whether newer coverage is the same story, a different story, or a materially new development.
annotating-task-lineage
Annotate Airflow tasks with data lineage using inlets and outlets. Use when the user wants to add lineage metadata to tasks, specify input/output datasets, or enable lineage tracking for operators without built-in OpenLineage extraction.
prompt-proximity-architecture
Turn an approved measurement charter, ICPs, and buyer jobs into a budget-aware prompt coverage blueprint across proximity bands, aided status, information acts, journey states, roles, locales, evidence grades, partitions, and measurement lanes. Use before prompt wording to define required, optional, and prohibited…
relevance-coarse-filter
Cheap, high-recall first-pass filter that removes obvious junk from a detector candidate pool before expensive story-origin research and PR judgment. Decides keep, monitoronly, or reject — never ranks, writes angles, verifies dates, or decides whether to pitch.