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 agentmods add instructions/deepcogneural/html-artifact-report-skill/agents-mdgit clone --depth 1 https://github.com/DeepCogNeural/html-artifact-report-skillWrote 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/instructions/deepcogneural/html-artifact-report-skill/agents-md)<a href="https://agentmods.dev/instructions/deepcogneural/html-artifact-report-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/deepcogneural/html-artifact-report-skill/agents-md.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 | $0.00200 | $0.00200 |
| Opus 5 | $0.00100 | $0.00100 |
| Sonnet 5 | $0.00040 | $0.00040 |
| Haiku 4.5 | $0.00020 | $0.00020 |
Grade A, and why
html-artifact-report-skill AGENTS.md 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 5d 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.
What it actually says
Agent Guide
This repository contains one agent skill: html-artifact-report.
What to read first
Contract: SPEC.md. Runtime: SKILL.md. Allowed components: components/report-components.md. Examples show the shape.
Core rule
The output is always two aligned files:
artifact.htmlfor humans.artifact.jsonfor agents and automation.
Do not create a pretty HTML report without a manifest. Do not create a manifest that cannot be cross-checked against the HTML.
Verification
Run the verification commands listed in SKILL.md before saying done.
Editing rules
- Keep v1 focused on one canonical report profile.
- Do not add a GUI app, live preview server, social-card templates, or document conversion pipeline.
- Keep examples real enough to validate the contract.
- Add negative fixtures when tightening a checker.
- If a local evidence file is cited in
artifact.json, include it insource_hashes.
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.
- 5d ago First seen · 29 lines · 200 tokens per session scan A 74d48765f319
html-artifact-report-skill AGENTS.md is an instructions file published in the GitHub repository DeepCogNeural/html-artifact-report-skill (2 stars, last pushed 1mo ago), licensed MIT. It adds 200 tokens to every session, about $0.0010 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 instructions, from other repositories
llm-wiki-agent GEMINI.md
Gemini CLI instructions for SamurAIGPT/llm-wiki-agent, covering llm wiki agent — schema & workflow instructions, how to use, directory layout, page format and ingest workflow.
llm-wiki AGENTS.md
Instructions for BogdanovychA/llm-wiki, covering інструкції для агентів: хранитель llm wiki, 1. структура каталогів, 2. загальні конвенції, 3. шаблони сторінок та стандарти форматування and назви файлів.
LLM-Wiki AGENTS.md
Instructions for TrueHOOHA/LLM-Wiki, covering llm wiki schema, mission, okf conformance, non-negotiables and directory layout.
docsift CLAUDE.md
Instructions for anishmoncivarghese/docsift, covering docsift, key documents (read before making product decisions), commands, architecture (src layout, package docsift) and hard rules.
librarian-cli CLAUDE.md
Claude Code instructions for Terobyte/librarian-cli, covering claude.md — libby / librarian, раскладка, команды, критический инвариант: golden не трогать and архитектура.
security-knowledge-base AGENTS.md
Instructions for dinosn/security-knowledge-base, covering security knowledge base agent contract, purpose and boundary, authority and trust, required startup sequence and agent permissions.