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-patterns-wave-03git clone --depth 1 https://github.com/AgentsKit-io/agentskit-registryWrote 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/agents/agentskit-io/agentskit-registry/application-patterns-wave-03)<a href="https://agentmods.dev/agents/agentskit-io/agentskit-registry/application-patterns-wave-03"><img src="https://agentmods.dev/badge/agents/agentskit-io/agentskit-registry/application-patterns-wave-03.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 | $0.00000 | $0.02676 |
| Opus 5 | $0.00000 | $0.01338 |
| Sonnet 5 | $0.00000 | $0.00535 |
| Haiku 4.5 | $0.00000 | $0.00268 |
Grade A, and why
application-patterns-wave-03 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 3d 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 — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Application patterns — Wave 03
Wave 03 expands the Registry showcase into domain workflows that benefit from structured outputs, explicit evidence gaps, and a human decision boundary. Every pattern below uses synthetic input and is a starting point for inspection, not evidence of customer impact, professional advice, compliance, safety, or production readiness.
Shared run contract
npx agentskit add <agent-id>
npm test -- --run registry/<agent-id>/agent.test.ts
Use a configured adapter or the credential-free demo path where supported. Inspect the typed result, missing evidence, and review requirement. Never treat a generated result as a clinical, financial, legal, insurance, employment, education, sales, purchase, coverage, eligibility, or go/no-go decision.
Health, finance, and regulated review
Chart Redactor — deterministic PHI backstop
- Agent: clinical-chart-redactor
- Try: Redact a synthetic chart containing an email, phone number, MRN, DOB, and clinical findings. Keep findings intact and report the identifiers removed.
- Inspect: deterministic second-pass redaction, preserved clinical content, structured output, and uncertainty about identifiers outside the configured rules.
- Next contribution: add a synthetic identifier fixture that the model misses but the deterministic scanner must remove.
- Human boundary: validate de-identification rules, privacy obligations, and clinical use before handling real records.
Intake Triage — red flags cannot be downgraded
- Agent: clinical-intake-triage
- Try: Classify synthetic patient messages as emergency, urgent, routine, administrative, or unclear, including one red-flag message and one incomplete message.
- Inspect: deterministic red-flag escalation, no downgrade path, rationale, missing context, and human-triage routing.
- Next contribution: add a fixture where vague wording must remain unclear instead of becoming routine.
- Human boundary: this is a routing aid, not diagnosis, treatment, or emergency advice.
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.
- 3d ago First seen · 177 lines · 0 tokens per session scan A dfa795dfefdf
application-patterns-wave-03 is an agent published in the GitHub repository AgentsKit-io/agentskit-registry (5 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,676 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
chaos-monkey
You are the Chaos Monkey ("Kaos Maymunu") — a mutation-testing saboteur for the WrongStack fleet. Your job is to prove whether a test suite actually pins down the code it claims to cover, by deliberately breaking that code and watching which mutants survive.
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.
memory-curator
Agent "memory-curator" from WrongStack/WrongStack, covering core responsibilities and output.
android
Agent "android" from WrongStack/WrongStack, covering working rules and output.
backend
You are the Backend agent. Your job is server-side logic: services, business rules, persistence wiring, and reliable request handling.
compliance
You are the Compliance agent. Your job is license, privacy, and regulatory review: check dependency licenses, data-handling, and control coverage against GDPR/SOC2-style requirements.