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 skills add dkharlanau/agent-ready-web-profile --skill arwp-portfolio-fleetgit clone --depth 1 https://github.com/dkharlanau/agent-ready-web-profileWrote 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/dkharlanau/agent-ready-web-profile/arwp-portfolio-fleet)<a href="https://agentmods.dev/skills/dkharlanau/agent-ready-web-profile/arwp-portfolio-fleet"><img src="https://agentmods.dev/badge/skills/dkharlanau/agent-ready-web-profile/arwp-portfolio-fleet/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/dkharlanau/agent-ready-web-profile/arwp-portfolio-fleet"><img src="https://agentmods.dev/badge/skills/dkharlanau/agent-ready-web-profile/arwp-portfolio-fleet.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 | $0.00076 | $0.00514 |
| Opus 5 | $0.00038 | $0.00257 |
| Sonnet 5 | $0.00015 | $0.00103 |
| Haiku 4.5 | $0.00008 | $0.00051 |
Grade A, and why
arwp-portfolio-fleet 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 — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ARWP Portfolio Fleet
Use this skill when the unit of work is a portfolio rather than one repository. Keep one workspace manifest outside target repositories when it contains machine-specific checkout paths.
Workflow
Start with the cheapest current evidence:
- Run
arwp-portfolio fleet-check <workspace.json>to validate the manifest. - Run
arwp-portfolio fleet-inspect <workspace.json> --jsonbefore opening repositories individually. This observes local Git/profile/discovery state without fetching remotes or changing files. - Group the result into missing checkouts, invalid or mismatched profiles, missing discovery files, preserved dirty worktrees, and clean sites.
- Read a target repository's instructions before changing that site. Use the existing Growth Loop and site-preparation skills for implementation.
Use fleet-live when current public availability matters. It performs bounded public HTTPS reads of each canonical homepage and profile, omits bodies from the receipt, and does not prove deployed commit identity, indexing, ranking or AI citation.
Use fleet-verify only after reviewing each site's explicit checks arrays. Commands run without a shell, sequentially within each checkout and concurrently only across different sites. Dirty worktrees are skipped unless the user specifically includes them; never enable --allow-dirty as a convenience. The receipt keeps the executable, argument count and argument hash rather than argument values; output is represented by byte counts and hashes so portfolio receipts do not collect logs or secrets. If a check changes a working tree, report it and preserve the files.
Select the next site from evidence and learning value: protect existing demand and migrations, then repair invalid profiles or broken discovery, then improve a page with a real intent and measurable useful action. Do not turn missing data into zero or apply one generic patch everywhere.
For manifest fields and state meanings, read references/workspace-contract.md. To convert an existing inventory with sites[].id, checkout, and site_url, use fleet-init; review the generated profile paths and add only known-safe check argument arrays.
What ships with it
2 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 · 27 lines · 76 tokens per session scan A bb0553d82f57
arwp-portfolio-fleet is a skill published in the GitHub repository dkharlanau/agent-ready-web-profile (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 76 tokens to every session and 514 once invoked, about $0.0004 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 2026-09-09.
Other skills, from other repositories
agentlas-operations
A set of operating procedures for running Agentlas, a system for coordinating agents, reusable workforces, automation graphs, and shared agent resources. It covers candidate selection, graph creation, asset discovery, and memory rules.
crm-operations
Resolve and safely create/update demo CRM contacts, deals, activity notes and follow-up tasks with revision checks and an atomic audit trail. Use for business-object operations; do not clean spreadsheets, analyze business performance or send customer messages.
web-builder
Inspect an existing web project and create or modify a working local page from a purpose, audience, sections, style and constraints brief. Use for building a website; leave final browser QA to webapp-testing and publishing to vercel-deploy.
p5js
Use when users request: p5.js sketches, creative coding, generative art, interactive visualizations, canvas animations, browser-based visual art, data viz, shader effects, or any p5.js project.
claude-design
Design one-off HTML artifacts (landing, deck, prototype).
pretext
Use when building creative browser demos with @chenglou/pretext — DOM-free text layout for ASCII art, typographic flow around obstacles, text-as-geometry games, kinetic typography, and text-powered generative art. Produces single-file HTML demos by default.