application-patterns

A catalogue of small examples showing how Registry agents can handle defined tasks using sample input and typed output. Registry agents are reusable coding-agent workflows.

In plain words
What is it for?
Use it to test agent patterns such as checking conflicting claims, reviewing structured results, and contributing improved examples.
Why use it?
It gives developers a focused way to try an agent, inspect its result, and identify what needs review before using it for real work.

Agent

Install

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.

agentmods
npx agentmods add agents/agentskit-io/agentskit-registry/application-patterns
Clone the repo
git clone --depth 1 https://github.com/AgentsKit-io/agentskit-registry
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,365 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 00a18ff9d5d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

docs/agents/application-patterns.md · 138 lines

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

  1. Install the agent with npx agentskit add <agent-id>.
  2. Run the focused test named in the linked human guide.
  3. Try the synthetic prompt below with a configured adapter or the credential-free demo path where supported.
  4. Inspect the typed output, gaps, and review requirement; do not treat a generated answer as approval.
  5. 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.

Read the full file on GitHub · 138 lines

Changes

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.

  1. 2d ago First seen · 138 lines · 0 tokens per session scan A 00a18ff9d5d3

Subscribe to this mod's changes

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.

Related

Other agents, from other repositories