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 agentproto/ts --skill news-mediagit clone --depth 1 https://github.com/agentproto/tsWrote 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/agentproto/ts/news-media)<a href="https://agentmods.dev/skills/agentproto/ts/news-media"><img src="https://agentmods.dev/badge/skills/agentproto/ts/news-media.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 5.1 | $0.00065 | $0.01039 |
| Opus 5 | $0.00032 | $0.00519 |
| Sonnet 5 | $0.00013 | $0.00208 |
| Haiku 4.5 | $0.00006 | $0.00104 |
Grade A, and why
news-media 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 8d 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
News / media (lemonde.fr, etc.) — recon plan
Different pattern from social. News content lives in the HTML article body (not a social GraphQL API), so here readability extraction wins — API-first does NOT apply. The two real gates are (1) the CMP consent wall and (2) the paywall/subscriber session. Worked example: lemonde.fr (probed live).
The two gates
1. CMP consent wall (EU sites — the FIRST blocker) ✅ handled live
Validated on lemonde.fr: the accept button is
"Accepter et continuer"— snapshot → click it →hasConsentflips false → true (euconsent/didomi cookie set), wall cleared for the session. (Other labels below for other CMPs.)
Le Monde shows a full GDPR consent wall before content: "L'accès gratuit au
site … subordonné à votre consentement" with button "Gestion des cookies",
"À quoi servent les cookies ?", and accept/subscribe choices. Until handled,
content + scraping are blocked.
- Handle it:
take_snapshot→ find the accept button (labels vary:"Accepter et fermer"/"Tout accepter"/"J'accepte"/"Continuer sans accepter"/ sometimes only"S'abonner"as the consent-choice) →clickit. - Persists a consent cookie (
euconsent-v2/didomi_token/sp_*) → no re-prompt that session. (Observed pre-consent cookies:atauthority,pa_privacy,_pctx,lmd_pa;hasConsent:falseuntil accepted.) - CMP vendors are reused across sites: Didomi (lemonde, many FR),
Sourcepoint (
sp_), OneTrust (#onetrust-accept-btn-handler), Quantcast/TCF. Recognize the vendor → known accept selector.
2. Paywall / subscriber session
Full articles need a logged-in subscriber cookie. Not logged in → only free/
metered articles + "Article réservé aux abonnés". With the user's subscriber
session in the cloned profile, full text renders. (Le Monde here: NOT subscribed
→ exclusive content gated.) See the cookies section in the browser skill for
injecting a synced subscriber session.
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.
- 8d ago First seen · 84 lines · 65 tokens per session scan A 654f36a276ed
news-media is a skill published in the GitHub repository agentproto/ts (5 stars, last pushed today), licensed Apache-2.0. It adds 65 tokens to every session and 1,039 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 2026-08-31.
Other skills, from other repositories
playwright
Use when the task requires capturing or automating a real browser from the terminal.
playwright-cli
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
browser-tools
Security wrapper over the upstream agent-browser skill, adding URL blocklisting, rate limiting, robots.txt enforcement, and scraping guardrails. Use when automating browser workflows that need safety limits.
skill-creator-primer
You MUST load this skill before the skill-creator skill AND before making ANY change to, or conducting a review of ANY Agent Skill. Triggers include creating, editing, reviewing, or contributing to any part of an Agent Skill (description, frontmatter, body, references, scripts, trigger evals, conflicts, etc).
llm-wiki
Use when building or maintaining a self-contained personal knowledge base (an LLM wiki) in plain markdown. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki health, auditing article claims against their sources, critiquing a wiki source's reasoning, superseding stale knowledge, 'add to…
extract-wisdom
Extract wisdom, insights, and actionable takeaways from YouTube videos, blog posts, articles, or text files. Use when asked to extract wisdom or key insights from a given content source.