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-discoverabilitygit 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-discoverability)<a href="https://agentmods.dev/skills/dkharlanau/agent-ready-web-profile/arwp-discoverability"><img src="https://agentmods.dev/badge/skills/dkharlanau/agent-ready-web-profile/arwp-discoverability/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-discoverability"><img src="https://agentmods.dev/badge/skills/dkharlanau/agent-ready-web-profile/arwp-discoverability.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 | $0.00046 | $0.01162 |
| Opus 5 | $0.00023 | $0.00581 |
| Sonnet 5 | $0.00009 | $0.00232 |
| Haiku 4.5 | $0.00005 | $0.00116 |
Grade A, and why
arwp-discoverability 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 — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ARWP discoverability
Use this repository's corpus and playbook to turn a site's real value into content people can find, evaluate and use. The ARWP manifest describes interfaces; it does not confer ranking or AI recommendation priority.
Workflow
Start with arwp-growth-loop; it remains the default orchestrator. This specialist supplies implementation choices, not a second policy or outcome system. Follow each practice's growth_hypothesis_ids and recommendation_rule_ids into the current native registries; mappings are routing context, not an endorsement. Carry selected site actions through the existing adoption record, Growth experiment and change receipt. Use BraidGraph for shared provenance; do not mint a disconnected graph.
Choose work from evidence
Inspect repository instructions, dirty state, the canonical hostname/path and the authoritative build output. Read the site's actual offer, content and measurement scope. Prefer fixing lost access or an existing useful landing page before adding another page. Preserve edits owned by other work.
Search the corpus with node bin/arwp.mjs discoverability --search="comparison" --json from the ARWP checkout (or arwp from an installed package). Read the implementation, verification, source notes and evidence level for the few matching tactics. documented means the linked guidance supports the practice; it does not establish a ranking effect. Recheck sources when advice, feature eligibility or prices may have changed.
Read the selected pattern's pattern_version, lifecycle, review and review.support before applying it. A null review date is unknown, not failed or verified. Check the linked section and support note for the exact proposed mechanism. Follow a deprecated pattern's replacement when applicable; do not silently select retired guidance.
Prefer the library's version-pinned export. For manual configs, copy corpus_version, the canonical fingerprint corpus_sha256, and the selected tactic_versions from the actual corpus using the version contract. When pins fail validation, inspect the change and reselect applicable revisions; do not delete pins just to make an old plan pass. Preserve historical plans as they were issued.
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 First seen · 52 lines · 46 tokens per session scan A 74142fa8972c
arwp-discoverability is a skill published in the GitHub repository dkharlanau/agent-ready-web-profile (0 stars, last pushed today), licensed Apache-2.0. It adds 46 tokens to every session and 1,162 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 2026-09-09.
Other skills, from other repositories
hephaestus-network
Use when the user types $hephaestus-network, /hep-network, or /agentlas-network, mentions @Hephaestus, or asks Agentlas to staff a durable goal from registered Local, owner Cloud, and public Hub agents or teams. The active host LLM staffs each turn; the exact roster remains goal-bound until explicit completion.
routing-card-authoring
Use whenever a build emits or repairs .agentlas/routing-card.json — the shared card contract for the single-agent builder, the team builder, and the packager. States what belongs in every field, which fields the hub can actually match on, and which fields silently break matching when a sentence leaks into them.
hephaestus-upload
Use when the user types $hephaestus-upload, /hep-upload, or /agentlas-upload, or asks to upload, publish, or list an Agentlas agent or team. Ask Cloud (private) vs Agentlas Hub (public) FIRST, then publish through the bundled Hephaestus gate.
hep-network
Staff a task from registered Local, owner Cloud, and public Hub agents.
hep-upload
Upload an Agentlas agent after asking Cloud vs Hub first.
session-agent-builder
Turn the current interactive conversation into an owner-reviewed reusable Agentlas agent; accept JSON or JSONL only for explicit terminal and automation runs.