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 OOBE-PROTOCOL/sap-mcp --skill sap-agent-registrygit clone --depth 1 https://github.com/OOBE-PROTOCOL/sap-mcpWrote 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/oobe-protocol/sap-mcp/sap-agent-registry)<a href="https://agentmods.dev/skills/oobe-protocol/sap-mcp/sap-agent-registry"><img src="https://agentmods.dev/badge/skills/oobe-protocol/sap-mcp/sap-agent-registry/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/oobe-protocol/sap-mcp/sap-agent-registry"><img src="https://agentmods.dev/badge/skills/oobe-protocol/sap-mcp/sap-agent-registry.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 | $0.00000 | $0.01652 |
| Opus 5 | $0.00000 | $0.00826 |
| Sonnet 5 | $0.00000 | $0.00330 |
| Haiku 4.5 | $0.00000 | $0.00165 |
Grade A, and why
sap-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 9d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAP Agent Registry
Use this skill for SAP agent identity, registration, profile updates, activation state, global directory listing, and agent profile inspection.
First Steps
- Call
sap_profile_current. - Call
sap_protocol_invariantsbefore registry writes when treasury, fee, hosted/local routing, or lifecycle-complete rules are unclear. - For registration, profile-image updates, Metaplex identity, SNS linking, or
full identity setup, call
sap_agent_identity_planbefore any write. It is free and returns normalized fields, local-signer routing, metadata contract, forbidden actions, and verification checklist. - Use low-cost exact/base micro-reads before broad discovery:
sap_agent_context,sap_get_agent,sap_get_agent_profile,sap_get_agent_stats,sap_is_agent_active,sap_get_global_state, andsap_list_agentswithlimit <= 20,view: "compact", andincludeProtocolIndexes: false. - Call
sap_get_network_overviewfor ecosystem counters when needed. - Use
sap_discover_agentswithquery,wallet,protocol, orcapabilityfor targeted read-premium hosted directory reads when micro-read reads are not enough. - Use
sap_list_all_agentsfor global current agent lists and followpagination.nextCursorfor additional pages.
Tools
sap_register_agentsap_protocol_invariantssap_agent_identity_plansap_agent_contextsap_agent_next_actionsap_update_agentsap_deactivate_agentsap_reactivate_agentsap_close_agentsap_get_agentsap_get_agent_profilesap_get_agent_statssap_get_global_statesap_get_network_overviewsap_list_agentssap_list_all_agentssap_is_agent_activesap_report_callssap_update_reputation_metrics
Routing
- Hosted accountless SAP MCP cannot sign user-owned registry writes. If
sap_register_agent,sap_update_agent, or another registry write returnshosted_local_signer_required, no x402 payment was charged. For agent registration, call the localsap_payments.sap_payments_register_agentbridge with the same fields andconfirm: true; it signs locally with the active SAP MCP profile. For agent profile, image, metadata, capability, protocol, pricing, or x402 endpoint updates, call localsap_payments.sap_payments_update_agentwith the same update fields andconfirm: true. For other registry writes, run the write on the local SAP MCP profile or use a production unsigned builder/finalizer flow when available. - Before any retry after
payment_required,hosted_local_signer_required,BlockhashNotFound, timeout, missingsap_payments, or a submitted signature that did not confirm, callsap_agent_next_action. Follow itssafeToRetryNow,nextTool, andforbiddenActionsfields. - Agent pictures must be public metadata, not desktop file paths. Upload the
image or metadata JSON to IPFS, Arweave, Kommodo, or HTTPS, then set
agentUri/metadataUriwithsap_payments_update_agent. - After
sap_payments_register_agent, do not stop at a Solscan link. Verifysuccess,agentRegistered,agentPda,confirmationStatus,protocolComplete, andprotocolFee.status. A complete registration should show the expected protocol fee credited to treasuryJ7PyZAGKvprCz4SQ5DKBLAHstJxgVqZcz6kguUoWpP7P. Ifsuccessis false butagentRegisteredis true, the account may exist but SAP registration is not protocol-complete. Report the integrity issue and do not retry automatically. - After
sap_payments_update_agent, fetch the agent profile again and verify the changed fields. For image/profile updates,agentUriormetadataUrimust resolve to public metadata containing the image URL. - If
sap_payments_update_agentreturns Anchor 3012,AccountNotInitialized, or mentionspricing_menu, do not run runtime repair and do not retry the same write. This means the write reached the SAP on-chain program but a required registry lifecycle PDA is missing or stale. Callsap_agent_next_actionandsap_protocol_invariants, then upgrade the SDK/server or use the initializer path before retrying. - For full agent identity setup, follow
docs/16_AGENT_IDENTITY_REGISTRY_PIPELINE.md: SAP registration first, optional Metaplex/MPL Core identity, optional SNS domain and records, then a final SAP update that pointsmetadataUriat the public metadata document. - "Find XONA Agent" or "find an agent by name" means
sap_discover_agentswithquery. - "Find x402 agents" means
sap_discover_agentswithhasX402Endpoint: true. - "List all agents" means first call free
sap_list_agentswithlimit <= 20,view: "compact", andincludeProtocolIndexes: false; then use paidsap_list_all_agentswithpagination.nextCursorif the user wants more, full rows, or ecosystem-scale enumeration. - "Agent by wallet" means
sap_get_agentorsap_get_agent_profile. - "Is this agent live?" means
sap_is_agent_active. - "Network totals" means
sap_get_network_overview.
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.
- 9d ago First seen · 135 lines · 0 tokens per session scan A 6c48a2403bce
sap-agent-registry is a skill published in the GitHub repository OOBE-PROTOCOL/sap-mcp (3 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,652 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…