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 umputun/agterm --skill html-doc-overlaygit clone --depth 1 https://github.com/umputun/agtermWrote 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/umputun/agterm/html-doc-overlay)<a href="https://agentmods.dev/skills/umputun/agterm/html-doc-overlay"><img src="https://agentmods.dev/badge/skills/umputun/agterm/html-doc-overlay/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/umputun/agterm/html-doc-overlay"><img src="https://agentmods.dev/badge/skills/umputun/agterm/html-doc-overlay.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 | $0.00165 | $0.02292 |
| Opus 5.5 | $0.00066 | $0.00917 |
| Sonnet 5.5 | $0.00033 | $0.00458 |
| Haiku 4.5 | $0.00016 | $0.00229 |
Grade A, and why
agdoc 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 17d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agdoc
Build one static HTML page about a subject from the current work and show it in this session's agterm
overlay. scripts/show.sh FILE does the showing; assets/<design>.html carries the look.
1. Settle the brief
The brief is a subject plus an angle.
- Arguments given: the whole string is the brief. Take the subject from it (
#123,pr 45, a URL, a plan name, a file or package, a free-form topic) and the angle from any audience cue ("business point of view", "for a reviewer", "for someone new to this"). Extra instructions in it ("only the risks", "compare with X") override the default outline below. - No arguments: gather candidates, most specific first:
- what the conversation is working on right now - an issue or PR under review, a plan being executed, an investigation or design being discussed, the change just made;
- repo state - the current branch's PR or MR through the forge CLI step 3 selects, when there is
one, commits ahead of the default branch, uncommitted changes, an in-progress plan in
docs/plans/.
- One candidate clearly dominates (the conversation is plainly about it) → take it, technical angle.
- Otherwise the subject becomes a question (step 2): up to 4 variants, most likely first and marked
(Recommended)with the reason in its description. Each label names subject and angle ("PR #45 - what it changes", "Issue #12 - business impact"); each description says what the page will contain. The built-in Other answer is the custom-instruction path, so add no option for it. - A
#Nwhose kind is unknown on GitHub:gh api repos/{owner}/{repo}/issues/N --jq '.pull_request != null'; on another forge, its CLI's equivalent.
2. Choose the design
| Design | Template | Look | Fits |
|---|---|---|---|
| Editorial | assets/editorial.html |
serif headings, hero with key numbers, pinned numbered index, cards, pipelines, timelines | explaining a topic, code area, skill or plan |
| Brief | assets/brief.html |
one screen, two at most: masthead, bottom line, a grid of labelled fact blocks | status of a PR, issue, branch or release; a quick overview |
| Classic | assets/classic.html |
plain reference page, top contents bar, pills and callouts | long reference material read top to bottom |
What ships with it
5 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.
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.
- 17d ago First seen · 131 lines · 165 tokens per session scan A 74f7c74f72dc
agdoc is a skill published in the GitHub repository umputun/agterm (674 stars, last pushed today), licensed MIT. It adds 165 tokens to every session and 2,292 once invoked, about $0.0007 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 2026-09-29.
Other skills, from other repositories
kami-landing
Produce a print-grade single-page kami (紙 / 纸) document — warm parchment canvas, ink-blue accent, serif at one weight, no italic, no cool grays. The output reads like a professional white paper or studio one-pager, not an app UI. Multilingual by design (EN · zh-CN · ja). One self-contained HTML file, zero dependencies.
html-ppt-weekly-report
Team weekly / status-update deck — corporate clarity, 8-cell KPI grid, shipped list, 8-week bar chart, next-week table. Use for 周报, business reviews, team status updates, and exec dashboards.
pptx-html-fidelity-audit
Audit a python-pptx export against its source HTML deck, identify layout/content drift (footer overflow, cropped content, missing italic/em, lost styling, off-rhythm spacing), and re-export with strict footer-rail + cursor-flow layout discipline. Use this skill whenever the user has a .pptx that was generated from an…
clinical-case-report
Structured medical case presentation for clinical rounds, conferences, and documentation. Generates SOAP-format or narrative case reports with physiologically accurate vitals, labs, and evidence-based plans. Use when the brief mentions "case report", "case presentation", "SOAP note", "clinical case", "ward rounds"…
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
digital-eguide
A two-spread digital e-guide preview — page 1 is a cover (display title, author, "What's inside" stats, table of contents teaser); page 2 is a spread (lesson body with pull-quote and a step list). Lifestyle / creator brand tone. Use when the brief asks for an "e-guide", "digital guide", "lookbook", "lead magnet"…