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/dkharlanau/agent-ready-web-profilenpx agentmods add skills/dkharlanau/agent-ready-web-profile/arwp-future-searchWrote 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-future-search)<a href="https://agentmods.dev/skills/dkharlanau/agent-ready-web-profile/arwp-future-search"><img src="https://agentmods.dev/badge/skills/dkharlanau/agent-ready-web-profile/arwp-future-search/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-future-search"><img src="https://agentmods.dev/badge/skills/dkharlanau/agent-ready-web-profile/arwp-future-search.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 | $0.00069 | $0.01060 |
| Opus 5 | $0.00034 | $0.00530 |
| Sonnet 5 | $0.00014 | $0.00212 |
| Haiku 4.5 | $0.00007 | $0.00106 |
Grade A, and why
arwp-future-search 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ARWP Future Search
Use this specialist after the normal Growth Loop has handled current crawl/index/canonical/content/identity blockers.
Goal
Improve the site's public machine-readable knowledge model without pretending every useful semantic mechanism is a documented ranking factor.
current foundation → semantic graph → evidence graph → retrieval feedback → agent operability → experiment → verify → measure → promote/retire
Source of truth
Read:
registry/future-search-experiments.json;docs/FUTURE-SEARCH-LAB.md;registry/page-semantics-profiles.json;- the target site's actual page/entity/content model.
Recheck primary sources when an experiment is watch, when the reviewed date is stale, or when a platform has recently changed behavior.
Workflow
- Protect the baseline. Do not let future-search experiments outrank current Search eligibility, canonical/indexability, truthful content, identity, crawler policy or user experience problems.
- Inventory canonical entities and pages. Reuse stable
@idvalues. Do not create duplicate nodes for the same Person, Organization, SoftwareApplication, Dataset, Service or other entity. - Add broader Schema.org semantics only when true. Current Google feature support is not the only reason to use a Schema.org property, but visible/grounded fact parity still applies. Useful relations can include
mainEntity,about,mentions,isPartOf,hasPart,subjectOf,citationandisBasedOn. - Compile the optional semantic index when useful. Run:
node bin/arwp-semantic-index.mjs build \
<page-manifest.json> <entity-catalog.jsonld> \
--output=<semantic-index.jsonld>
node bin/arwp-semantic-index.mjs check <semantic-index.jsonld>
Treat the aggregate file as an optional interoperability surface. Do not replace page-local JSON-LD, visible navigation, canonical HTML, sitemap or ordinary crawling.
5. Build evidence paths. For research/software/documentation pages, connect real datasets, methods, code, publications and downloadable artifacts through explicit relations where appropriate. Never create decorative evidence.
6. Use retrieval feedback. Where owner data exists, review joint Search Console query+page evidence and Bing grounding/citation evidence. Map intent to the strongest existing canonical page and evidence asset before proposing another URL.
7. Review agent operability. For interactive pages, prefer native semantic HTML and accurate ARIA role/name/state. Require rendered accessibility checks and browser-agent runtime tasks.
8. Keep action semantics gated. Do not declare a structured action unless the public capability is real and the target is accurate. Static metadata never authorizes side effects.
9. Use truthful change notification. Keep sitemap lastmod meaningful and use IndexNow/provider-specific notification only where supported. Submission is not indexing evidence.
10. Record the result as an experiment. Preserve implementation verification separately from external outcome evidence. Promote an experiment only after source review and repeatable utility; retire mechanisms that create maintenance cost or ambiguity without value.
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 · 81 lines · 69 tokens per session scan A 6ed3b426400f
arwp-future-search is a skill published in the GitHub repository dkharlanau/agent-ready-web-profile (0 stars, last pushed yesterday), licensed Apache-2.0. It adds 69 tokens to every session and 1,060 once invoked, about $0.0003 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 2026-09-08.
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.