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/kkenny0/card-skill/agents-mdgit clone --depth 1 https://github.com/KKenny0/card-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/kkenny0/card-skill/agents-md)<a href="https://agentmods.dev/instructions/kkenny0/card-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/kkenny0/card-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 | $0.00585 | $0.00585 |
| Opus 5 | $0.00293 | $0.00293 |
| Sonnet 5 | $0.00117 | $0.00117 |
| Haiku 4.5 | $0.00059 | $0.00059 |
Grade A, and why
card-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.
How it starts
The opening of the file, as written. The whole thing — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository instructions
Working principles
- Use PowerShell 7 (
pwsh) for PowerShell commands. - Start from the actual input, contract, renderer, and output artifact before changing behavior.
- Preserve user-owned untracked work. Do not stage, rewrite, or delete
HANDOFF.mdorprototypes/unless the user explicitly asks.
Source of truth and packaged mirror
- The repository root is the source of truth for
SKILL.md,README.md,README.zh-CN.md,VERSION,package.json,assets/,evals/,references/,schemas/, andscripts/. README.mdis the primary English product README. KeepREADME.zh-CN.mdaligned when product docs change.plugins/card-skill/skills/card-skill/is a generated installable mirror. Do not edit it independently.- After changing any packaged source, run
npm run package-skill, then inspect the resulting mirror diff. - Keep
VERSION, the root and packagedpackage.json, the root and packagedSKILL.mdfrontmatter,plugins/card-skill/.codex-plugin/plugin.json, and the version in.claude-plugin/marketplace.jsonsynchronized.
Contract boundaries
- Codex inline preview is a decision surface. It may select a render contract, but it must not bypass the normal schema, renderer, screenshot,
check-output, and PNG inspection chain. editorial-image.composition_required: truemeans the selected direction cannot be delivered by the default scaffold. Before rendering, provide bothcontent_htmlandcustom_css; validation and the renderer must reject an incomplete contract.scripts/lib/schema.jsowns runtime input validation. Files inschemas/document the public structured contract and must stay aligned with runtime validation.- Renderers own deterministic HTML generation.
scripts/check-output.mjsowns machine-checkable output defects; subjective composition quality remains a visual inspection responsibility. - Keep provider authentication and upstream semantics out of card renderers. Source adapters normalize external content before it reaches a render contract.
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 · 43 lines · 585 tokens per session scan A 3ada1dc55288
card-skill AGENTS.md is an instructions file published in the GitHub repository KKenny0/card-skill (5 stars, last pushed 18d ago), licensed MIT. It adds 585 tokens to every session, about $0.0029 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
agent-skill-manager AGENTS.md
AGENTS.md instructions for dees91/agent-skill-manager, covering skill manager agent brief, project intent, mandatory wiki routing, current target environment and discovery model.
forge-skills CLAUDE.md
Claude Code instructions for aneja5/forge-skills, covering forge-skills, project structure, the .forge/ handoff chain, skills by phase and conventions.
forge-skills AGENTS.md
AGENTS.md instructions for aneja5/forge-skills, covering agents.md, core rules, intent → skill mapping, define & specify and design.
claude-sports-analytics CLAUDE.md
Instructions for PuckAPI/claude-sports-analytics, covering hockey skills -- claude code instructions, public repo rules, never include, commit messages and code and content.
prismstack CLAUDE.md
Instructions for fagemx/prismstack, covering prismstack — developer handoff, project overview, directory structure, installation and testing.
DSPy-Programming-not-prompting-LMs-skills CLAUDE.md
Claude Code instructions for lebsral/DSPy-Programming-not-prompting-LMs-skills, covering dspy skills repository, conventions, workspace directory, repo structure and adding or updating a skill.