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 skills/tethral-inc/agentregistry/openclaw-skillnpx skills add Tethral-Inc/AgentRegistry --skill openclaw-skillgit clone --depth 1 https://github.com/Tethral-Inc/AgentRegistryWrote 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/tethral-inc/agentregistry/openclaw-skill)<a href="https://agentmods.dev/skills/tethral-inc/agentregistry/openclaw-skill"><img src="https://agentmods.dev/badge/skills/tethral-inc/agentregistry/openclaw-skill.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 5.1 | $0.00056 | $0.01985 |
| Opus 5 | $0.00028 | $0.00992 |
| Sonnet 5 | $0.00011 | $0.00397 |
| Haiku 4.5 | $0.00006 | $0.00198 |
Grade A, and why
acr-agent-registry 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 6d 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 — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ACR Agent Registry
Purpose
Register your composition with ACR, log every external interaction, and build an interaction profile you can query through behavioral lenses. If ACR observes that a component in your composition has elevated anomaly signals, you will receive a notification. ACR is a registry and notification layer — not a security check.
Setup
Set environment variable: ACR_API_URL=https://acr.nfkey.ai
On First Startup
- Check if you have a stored Ed25519 keypair + agent_id in your memory.
If not, generate a fresh keypair (use any Ed25519 library — Node's
node:cryptogenerateKeyPairSync('ed25519')or Python'scryptography.hazmat.primitives.asymmetric.ed25519). Persist the public_key and private_key as base64url-encoded raw bytes. - List all your installed skills. For each, read the SKILL.md file content.
- Sign a proof-of-possession payload:
- Let
now = Date.now()(unix ms). - Canonical message:
register:v1:{public_key}:{now} - Signature: Ed25519-sign that message with your private_key, encode base64url.
- Let
- POST to $ACR_API_URL/api/v1/register with: { "public_key": "<base64url raw Ed25519 pub key, 43 chars>", "registration_timestamp_ms": , "signature": "<base64url raw Ed25519 sig, 86 chars>", "provider_class": "openclaw", "composition": { "skills": ["skill_name_1", "skill_name_2", ...], "skill_hashes": [""] } }
- Store the returned agent_id. Reuse the SAME keypair forever — losing the private key means the agent identity is unrecoverable.
On Subsequent Startups
- Read your stored agent_id from memory.
- Check for skill updates: GET $ACR_API_URL/api/v1/skill-version/acr-agent-registry If a newer version exists, tell the user.
- ALWAYS call update_composition at session start with your current set of installed skills, MCPs, and tools. This is the single most important thing you can do for composition fidelity — the server uses your composition to tell which interactions are internal (your model using its own attached parts) versus external (those parts reaching outside).
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.
- 6d ago First seen · 205 lines · 56 tokens per session scan A 6c196d96958d
acr-agent-registry is a skill published in the GitHub repository Tethral-Inc/AgentRegistry (1 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 1,985 once invoked, about $0.0003 per session on Opus 5. 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 skills, from other repositories
phoenix-observability
Open-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations on datasets, or monitoring production AI systems with real-time insights.
langsmith-observability
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
sre-expert
Expert-level site reliability engineering, SLOs, incident management, and operational excellence. Use when the user mentions reliability, monitoring, incident management, SLOs, or observability, or when the task involves SRE Fundamentals, Reliability Practices, SRE Principles, or On-Call.
debugging-workflow
Find the cause of a defect by hypothesis and bisection rather than by guessing, then fix it behind a regression test. Use when the user reports a bug, a crash, a test that fails intermittently, a performance regression or a production incident, asks why code behaves unexpectedly, or when the task involves reproducing…
grafana-expert
Expert-level Grafana dashboards, visualization, data sources, alerting, and production operations. Use when the user mentions dashboards, visualization, monitoring, observability, or alerting, or when the task involves Grafana Architecture, Installation on Kubernetes, Data Sources, or Dashboard JSON.
linkerd-expert
Expert-level Linkerd service mesh management, traffic control, reliability, and production operations. Use when the user mentions service mesh, Kubernetes, microservices, mTLS, or observability, or when the task involves Linkerd Architecture, Mesh Injection, Traffic Management, or Reliability Features.