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 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/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<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="Reviewed on agentmods" width="80" 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 5.5 | $0.00022 | $0.00794 |
| Sonnet 5.5 | $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 1mo 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.
- 1mo 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 28d ago), licensed MIT. It adds 56 tokens to every session and 1,985 once invoked, about $0.0002 per session on Opus 5.5. 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
observability-phoenix
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.
aegis-code-review
Review an AEGIS PR, commit, branch or working-tree diff for concrete defects, requirement gaps and project-rule violations. Read-only unless fixes are requested; use audit-check for broad repository readiness checks.
aegis-diagnosing-bugs
Diagnose AEGIS process attribution, sensor, audit, IPC, renderer or performance regressions using a repeatable failure signal. Use for reported bugs; excludes broad architecture audits and feature planning.
testing
Design or update meaningful AEGIS Vitest tests, including CommonJS dependency seams, renderer tests and Svelte component environments.
aegis-tdd
Implement meaningful AEGIS features or regressions with one failing behavioral test and minimal implementation at a time. Use for TDD or test-first fixes; the existing testing skill owns Vitest harness details.
aegis-context
AEGIS architecture and source navigation. Use when implementing, debugging, testing, or explaining AEGIS behavior, or checking technical documentation against source.