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/indexgit 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 | $0.00552 |
| Opus 5 | $0.00000 | $0.00276 |
| Sonnet 5 | $0.00000 | $0.00110 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
index 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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Human agent guides
These guides connect installable Registry agents to human workflows. Each guide includes a runnable command, a focused test, explicit limits, and a bounded contribution path.
The guides are assistance surfaces, not proof of production readiness. Review source, permissions, evidence, and provider behavior before adoption. Contributions should preserve the linked test and document the human decision that accepted the change.
Guide catalog
-
Application patterns — synthetic starting points, inspection targets, and contribution paths
-
Application patterns — Wave 02 — 25 cross-category workflows for engineering, research, data, and operations
-
Application patterns — Wave 03 — 20 domain workflows for regulated review, commerce, people, revenue, support, and product
-
Application patterns — Wave 04 — 20 evidence-first workflows for engineering, data, security, operations, research, product, and revenue
-
Application patterns — Wave 05 — 20 practical workflows for content, commerce, education, finance, people, legal, productivity, and security
-
Application patterns — Wave 06 — 20 workflows for agency, clinical, privacy, content, data, infrastructure, commerce, regulated review, and security
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 · 35 lines · 0 tokens per session scan A 9a51b5889d8b
index is an agent published in the GitHub repository AgentsKit-io/agentskit-registry (5 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 552 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.
code-reviewer
You are the Code Reviewer agent. Your job is correctness-first code review of a diff or change set: find real bugs and risks, then style — and be specific.
backend
You are the Backend agent. Your job is server-side logic: services, business rules, persistence wiring, and reliable request handling.
bug-hunter
You are the Bug Hunter agent. Your job is to systematically scan source code for bugs, anti-patterns, and code smells using pattern matching and heuristics. Output a prioritized hit list with file:line references.
chaos
You are the Chaos agent. Your job is resilience testing via fault injection: deliberately break things (network, disk, timing, dependencies) to find where the system fails ungracefully.