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 aimeos/pagible --skill counselgit clone --depth 1 https://github.com/aimeos/pagibleWrote 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/aimeos/pagible/counsel)<a href="https://agentmods.dev/skills/aimeos/pagible/counsel"><img src="https://agentmods.dev/badge/skills/aimeos/pagible/counsel/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/aimeos/pagible/counsel"><img src="https://agentmods.dev/badge/skills/aimeos/pagible/counsel.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 | $0.00034 | $0.00871 |
| Opus 5.5 | $0.00014 | $0.00348 |
| Sonnet 5.5 | $0.00007 | $0.00174 |
| Haiku 4.5 | $0.00003 | $0.00087 |
Grade A, and why
counsel 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 6d 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Counsel Theme Design System
Direction
Use a calm, authoritative layout that lets clients trust the firm before the first call. Put the practice areas, the attorneys, the way to book a consultation, the costs and the urgent hotline first, followed by proof: years, matters, certified specialists and selected results. Show real people, offices and the city; avoid clichés like gavels on every page, handshake stock photos as the main visual or dramatic courtroom scenes.
Foundations
- Use only the markup and classes supplied by
./theme/views/. - Use system fonts (classic serif fonts for headings) and the existing
--pico-*variables. - Keep page content within a
1280pxmaximum width. - Use an ivory background and header, navy (
#0E2A47) for heroes, the footer and dark sections, brass (#7D5F2A) for links and accents on light backgrounds and gold (#C6A15B) only for rules, the first button and text on dark backgrounds, never for text on light backgrounds. - Use sharp corners, hairline borders and thin gold rules instead of shadows; dark sections show a faint diagonal pinstripe, eyebrows are uppercase and tracked, portraits are grayscale until hovered.
Components
- Hero: a navy hero with an eyebrow naming the firm and city, a short headline, two actions ("Book a consultation" and the practice areas) and a city skyline or building photo as background.
- Figures and badges: cards in the
figureslayout for founding year, matters, transaction volume and specialists, and in thebadgeslayout with brass line icons for partner-led work, specialists, languages and confidentiality. - Practice areas: four-column cards with a photo, a short text and a link; each practice area page names the responsible attorney, lists typical matters, answers cost and deadline questions and links a matching insight.
- Attorneys: four-column cards with portraits of the same ratio, the name as title and role, focus, certifications and languages as text; the team size matches the figures.
- Results: figure-style cards with the amount or outcome as title, always followed by the note that prior results don't guarantee a similar outcome.
- Fees: a
pricingelement with the initial consultation, hourly rates and fixed fees, prices plus VAT. - Process: a horizontal timeline from contact to resolution.
- Insights:
blogpages below the insights page, each with an article, key figures, a vertical step timeline, questions and a call to action that reminds readers it is no legal advice. - Consultation: a contact form with selects for the practice area and client type, a field for other parties for the conflict check and the matter in brief, plus the fees and a map with office hours, the hotline and directions.
- Footer: office hours with the hotline, practice areas, firm links including careers, imprint and privacy, contact and the disclaimer.
- Firm details: the
firmconfig adds the legal business JSON-LD, the action bar for phones, the top bar with the hotline, the consultation button in the header and the footer disclaimer.
What ships with it
60 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.
- .gitattributes 60 B
- composer.json 699 B
- database/seeders/CounselDemo.php 76 KB
- lang/af.json 144 B
- lang/ar.json 161 B
- lang/az.json 156 B
- lang/bg.json 187 B
- lang/ca.json 136 B
- lang/cs.json 151 B
- lang/da.json 138 B
- lang/de.json 151 B
- lang/el.json 214 B
- lang/en.json 131 B
- lang/es.json 138 B
- lang/et.json 151 B
- lang/fa.json 169 B
- lang/fi.json 147 B
- lang/fr.json 143 B
- lang/he.json 171 B
- lang/hr.json 143 B
- lang/hu.json 142 B
- lang/id.json 136 B
- lang/it.json 140 B
- lang/ja.json 160 B
- lang/km.json 215 B
- lang/ko.json 153 B
- lang/lt.json 152 B
- lang/lv.json 150 B
- lang/nl.json 143 B
- lang/no.json 138 B
- lang/pl.json 138 B
- lang/pt-BR.json 146 B
- lang/pt.json 139 B
- lang/ro.json 151 B
- lang/ru.json 211 B
- lang/sk.json 154 B
- lang/sl.json 138 B
- lang/sr.json 186 B
- lang/sv.json 143 B
- lang/th.json 215 B
- lang/tr.json 152 B
- lang/uk.json 219 B
- lang/vi.json 164 B
- lang/zh-TW.json 130 B
- lang/zh.json 130 B
- LICENSE 1.0 KB
- public/article.css 437 B
- public/before-after.css 2.1 KB
- public/cards.css 4.7 KB
- public/cms-lazy.css 8.4 KB
- public/cms.css 16 KB
- public/contact.css 2.1 KB
- public/cta.css 1.5 KB
- public/hero.css 4.7 KB
- public/i18n/ar.json 3.9 KB
- public/i18n/bg.json 4.4 KB
- public/i18n/cs.json 3.4 KB
- public/i18n/da.json 3.1 KB
- public/i18n/de.json 3.2 KB
- public/i18n/el.json 4.5 KB
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.
- 6d ago First seen · 47 lines · 34 tokens per session scan A f91f69eb150c
counsel is a skill published in the GitHub repository aimeos/pagible (596 stars, last pushed today), licensed MIT. It adds 34 tokens to every session and 871 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-10.
Other skills, from other repositories
api-designer
Designs production-grade APIs — REST, GraphQL, gRPC, and AsyncAPI patterns including pagination, versioning, error handling, rate limiting, and API governance. Use when the user asks to design APIs, create endpoints, build an API layer, write OpenAPI specs, or needs help with REST/GraphQL/gRPC service design.
api-design-first
Design-first API development skill. Generates OpenAPI 3.1 specifications, enforces REST design best practices, validates endpoints, handles versioning, pagination, error formatting, authentication patterns, rate limiting, and idempotency. Activates when users say "design an API", "create OpenAPI spec", "API endpoint"…
strapi-cms
Customisable headless CMS with Strapi.
api-design
Applies REST and GraphQL design principles to produce or review an API contract.
api-integration-architect
Design, implement, debug, and optimize API integrations with expert-level patterns for REST, GraphQL, webhooks, and authentication flows.
ada-plan-view-accessibility
Use when checking simplified ADA-derived plan-view bathroom accessibility constraints such as turning space, door clear width, toilet centerline, grab bars, and lavatory knee/toe clearance.