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 guanyang/open-agent-hub --skill knapgit clone --depth 1 https://github.com/guanyang/open-agent-hubWrote 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/guanyang/open-agent-hub/knap)<a href="https://agentmods.dev/skills/guanyang/open-agent-hub/knap"><img src="https://agentmods.dev/badge/skills/guanyang/open-agent-hub/knap/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/guanyang/open-agent-hub/knap"><img src="https://agentmods.dev/badge/skills/guanyang/open-agent-hub/knap.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 | $0.00050 | $0.00900 |
| Opus 5.5 | $0.00020 | $0.00360 |
| Sonnet 5.5 | $0.00010 | $0.00180 |
| Haiku 4.5 | $0.00005 | $0.00090 |
Grade A, and why
knap 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.
This is a copy
100% identical to knap — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knap
Use Knap CLI to render Markdown templates with variables, filters, and logic.
If not installed: npm install -g knap (requires Node.js 20 or later). Alternatively, use npx knap.
Run knap --help for available commands and options. Discover the language through the CLI's offline reference:
knap help syntax
knap help filters
knap help filter date
knap help tags
knap help tag for
Use the lists to find names, then request individual help for syntax, parameters, and examples with expected output.
Usage
Render a template with JSON variables:
knap render template.md --data article.json -o note.md
Supply a template and data inline:
knap render -t '# {{ title | trim }}' --data-json '{"title":"Hello"}'
Override a variable or pipe JSON data:
knap render template.md --data article.json --set 'title=Custom title'
cat article.json | knap render template.md --data -
Data must be a JSON object; its properties become template variables. --set overrides literal top-level keys with strings. Use JSON for nested objects, arrays, numbers, and booleans.
Choose one template source (file, -t, or stdin) and one data source (--data or --data-json). Only one input can read stdin. Without a template file or -t, Knap reads the template from stdin.
Output defaults to stdout. -o creates parent directories and overwrites the destination after rendering succeeds. Errors exit with status 1; diagnostics go to stderr. Warnings can accompany successful output.
Templates
Use {{ variable }} for values, | for filters, and {% ... %} for logic. For example, save this as template.md:
---
{{ title | yaml_property:"title" }}
{{ tags | yaml_property:"tags" }}
---
# {{ title | trim }}
{% if author %}
By {{ author }}
{% endif %}
{{ content }}
Use yaml_property for complete frontmatter properties so values are quoted and indented correctly. The CLI includes standard filters, but does not supply Web Clipper browser variables, selectors, prompts, or DOM-dependent HTML filters. Supply variables through JSON.
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 · 103 lines · 50 tokens per session scan A ef5666573358
knap is a skill published in the GitHub repository guanyang/open-agent-hub (981 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 900 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to knap, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
learn
Runs a six-phase research workflow from source bundle to publish-ready output. Use when researching an unfamiliar domain or compiling materials into one reference. Not for quick lookups or single-file reads.
36-anthropic-agents-kit-development
This page used to hold an archived copy of this skill. The archive now lives in the registry's data repository.
agent-architecture-planner
This page used to hold an archived copy of this skill. The archive now lives in the registry's data repository.
agent-browser-avibebuilder-claude-prime
This page used to hold an archived copy of this skill. The archive now lives in the registry's data repository.
agent-builder-keysersoose-claude-agent-builder
This page used to hold an archived copy of this skill. The archive now lives in the registry's data repository.
agent-communication-protocol-enuno-claude-command-and-c-2
This page used to hold an archived copy of this skill. The archive now lives in the registry's data repository.