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 Rustam-Z/hamroh --skill render-stylegit clone --depth 1 https://github.com/Rustam-Z/hamrohWrote 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/rustam-z/hamroh/render-style)<a href="https://agentmods.dev/skills/rustam-z/hamroh/render-style"><img src="https://agentmods.dev/badge/skills/rustam-z/hamroh/render-style/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/rustam-z/hamroh/render-style"><img src="https://agentmods.dev/badge/skills/rustam-z/hamroh/render-style.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00082 | $0.06708 |
| Opus 5.5 | $0.00033 | $0.02683 |
| Sonnet 5.5 | $0.00016 | $0.01342 |
| Haiku 4.5 | $0.00008 | $0.00671 |
Grade A, and why
render-style 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 1mo 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 — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: render-style
Reference skill (no <reminder> envelope required). Read it before
calling render_html and adapt the closest skeleton — don't redesign.
Tool names: call these by their registered names —
mcp__hamroh__render_htmlto render andmcp__hamroh__telegram_send_phototo deliver. The barerender_htmlis prose shorthand and matches no tool.
There are three layout modes; pick the one that fits the content:
- Dashboard — left-aligned title, stat tiles, bar rows, verdict. For metrics, scorecards, calibration reports.
- Timeline / pipeline — centered title, numbered steps in colored circles, each step a card. For lifecycles, flows, ordered processes.
- Architecture diagram — centered title, two-panel grid or stacked tiers, inline pills, connector arrows with labels, footer line. For systems, components, tier maps.
All three share the same tokens, fonts, and section-header style.
Tokens (paste these CSS vars verbatim)
--bg:#0e1828; /* page background */
--card:#1a2332; /* tile / card / track background */
--card2:#141d2c; /* nested panel background (slightly darker) */
--line:rgba(255,255,255,.06); /* dividers, tile borders */
--tx:#ffffff; /* primary text, big numbers */
--tx2:#9ba8bd; /* body / secondary */
--tx3:#6b7a91; /* uppercase labels, captions */
--blue:#3b82f6; /* neutral / info / partial / step 1 */
--green:#10b981; /* correct / positive / safe / step 3 */
--red:#ef4444; /* wrong / negative / stop / crash */
--amber:#f59e0b; /* pending / warning / step 4 */
--purple:#8b5cf6; /* command / owner / auth / step 5 */
--cyan:#06b6d4; /* IO / pipeline / step 2 */
--gray:#6b7280; /* N/A, unverifiable */
Color semantics:
- green — good outcome, safe path, "correct"
- blue — neutral, info, "partial", first step in a sequence
- red — bad outcome, "wrong", "stop", crash branch
- amber — pending, warning, "early", interrupt callout
- purple — command / owner / auth tier, end of sequence
- cyan — IO, network, pipeline middles
- gray — unknown, N/A, unverifiable
What ships with it
1 file 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.
- 1mo ago First seen · 405 lines · 82 tokens per session scan A 66abfe4cd8e8
render-style is a skill published in the GitHub repository Rustam-Z/hamroh (55 stars, last pushed 3d ago), licensed MIT. It adds 82 tokens to every session and 6,708 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
aav-vector-design-agent
Skill "aav-vector-design-agent" from FreedomIntelligence/OpenClaw-Medical-Skills, covering copyright notice, copyright (c) 2026 md babu mia, phd, all rights reserved, this code is proprietary and confidential and provenance: authenticated by md babu mia.
add-iron-proxy
Install or refresh Iron Proxy and its official Iron Control web console for NanoClaw. Use when selecting the Iron gateway, adding its management UI, configuring credentials and grants, or restoring the proxy, approval bridge, and agent guidance.
slack-agent-flow
Let an existing Slack agent create new agents that arrive as their own Slack bots — provisioned app, operator DM, and a shared three-way room, hot-started without a host restart.
add-codex
Use Codex (OpenAI's codex app-server) as a full agent provider — planning, tool orchestration, MCP tools, server-side history, session resume — alongside or instead of Claude. ChatGPT subscription or OpenAI API key, vault-only via the selected gateway. Per-group via ncl groups config update --provider codex. Distinct…
add-emacs
Add Emacs as a channel. Opens an interactive chat buffer and org-mode integration so you can talk to NanoClaw from within Emacs (Doom, Spacemacs, or vanilla). Local HTTP bridge — no bot token or external service needed.
add-github
Add GitHub channel integration via Chat SDK. PR and issue comment threads as conversations.