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 agents/agentskit-io/agentskit-registry/application-patternsgit clone --depth 1 https://github.com/AgentsKit-io/agentskit-registryWhat 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 | $0.00000 | $0.02365 |
| Opus 5 | $0.00000 | $0.01182 |
| Sonnet 5 | $0.00000 | $0.00473 |
| Haiku 4.5 | $0.00000 | $0.00236 |
Grade A, and why
application-patterns 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 2d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Application patterns
This catalog turns Registry agents into small, reviewable starting points. Each pattern uses synthetic input, names the output to inspect, and ends with a contribution path. The examples are demonstrations of the contract, not customer results or production-readiness claims.
How to use a pattern
- Install the agent with
npx agentskit add <agent-id>. - Run the focused test named in the linked human guide.
- Try the synthetic prompt below with a configured adapter or the credential-free demo path where supported.
- Inspect the typed output, gaps, and review requirement; do not treat a generated answer as approval.
- Improve the fixture or documentation through the linked activation issue.
Pattern catalog
Fact Checker — conflicting source review
- Agent:
content-fact-checker - Use when: an editorial claim has two sources that disagree on date, population, or wording.
- Synthetic prompt:
Check the claim "The pilot reduced review time by 30%" against Source A: internal timing notes, dated 2026-01-10, and Source B: published case note, dated 2026-02-01. The sources use different samples. - Inspect: claim status, source references, conflict description, missing evidence, and the human decision required before publication.
- Contribute: ACT-01 / #107.
Newsletter Author — accessible release note
- Agent:
content-newsletter-author - Use when: turning a verified technical change into a newsletter draft with clear structure and accessible language.
- Synthetic prompt:
Draft a short release note for a new deterministic test fixture. Audience: developers. Include one plain-language benefit, one limitation, headings, and an accessible link label. Do not invent adoption or performance results. - Inspect: audience fit, claim boundaries, headings, link text, and the review points a human editor must verify.
- Contribute: ACT-02 / #108.
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.
- 2d ago First seen · 138 lines · 0 tokens per session scan A 00a18ff9d5d3
application-patterns is an agent published in the GitHub repository AgentsKit-io/agentskit-registry (5 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,365 tokens. 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 agents, from other repositories
explore-companion
You are the Explore Companion. Your job is to make the leader faster, not to lead. The leader is already executing the main task; you run behind it, answer one narrow probe, and hand back just enough map that the leader does not spend its own context discovering where things are.
fleet-coordinator
Agent "fleet-coordinator" from WrongStack/WrongStack, covering working rules and output.
plugin-author
Agent "plugin-author" from WrongStack/WrongStack, covering working rules and output.
tools
Tools give agents the ability to interact with the outside world — reading files, making HTTP requests, connecting to MCP servers, calling APIs, or running custom Python functions. They are configured in the tools list of a role definition. A bare name (- search) enables a tool with defaults; a mapping adds options (…
acp-cline
You are Cline, a coding agent. You help write, edit, and navigate code. You operate by receiving tasks via ACP and returning results. When asked to code, make focused changes and explain them briefly.
acp-gemini-cli
You are Gemini CLI, a coding agent powered by Google's Gemini model. You help with code generation, editing, debugging, and best practices. You operate by receiving tasks via ACP and returning results.