sap-operations

sap-operations is a skill for Claude Code, Codex from OOBE-PROTOCOL/sap-mcp. It costs 0 tokens per session (1,038 once invoked), scanned A, original, MIT.

A guide for operating SAP Protocol features, a system for registering and managing software agents and their transactions. It covers agent identity, memory, reputation, payments, escrow, disputes, staking, and publishing tools.

In plain words
What is it for?
Use it to discover, register, update, deactivate, or close agents; manage profiles and memory; handle payments and escrow; and publish tools.
Why use it?
It provides the read-before-write and transaction-preview steps needed when working with protocol data or on-chain actions. This helps avoid unsafe or unexpected changes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to discover, register, update, deactivate, or close agents; manage profiles and memory; handle payments and escrow; and publish tools.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oobe-protocol/sap-mcp/sap-operations
Install

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.

Any agent
npx skills add OOBE-PROTOCOL/sap-mcp --skill sap-operations
Clone the repo
git clone --depth 1 https://github.com/OOBE-PROTOCOL/sap-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for sap-operations

README.md
[![agentmods](https://agentmods.dev/badge/skills/oobe-protocol/sap-mcp/sap-operations.svg)](https://agentmods.dev/skills/oobe-protocol/sap-mcp/sap-operations)
Your own site
<a href="https://agentmods.dev/skills/oobe-protocol/sap-mcp/sap-operations"><img src="https://agentmods.dev/badge/skills/oobe-protocol/sap-mcp/sap-operations.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,038 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01038
Opus 5 $0.00000 $0.00519
Sonnet 5 $0.00000 $0.00208
Haiku 4.5 $0.00000 $0.00104

Measured 7d ago against content hash 716a1cc5d387, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

sap-operations 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 7d 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.

skills/sap-operations/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SAP Operations

Use this skill for SAP Protocol registry, agent lifecycle, memory, reputation, x402 payments, escrow, settlement, disputes, staking, and tool publishing.

This skill corresponds to upstream SAP SDK v1.0.x domains such as sap-overview, sap-client, sap-advanced, sap-memory, sap-merchant, and sap-enterprise.

Operating Pattern

  1. Inspect sap_profile_current.
  2. Use read tools before write tools.
  3. For write operations, explain the on-chain action and expected cost.
  4. For transactions or direct signing, preview first with sap_preview_transaction.
  5. Never read keypair files.

Agent Registry

Use:

  • sap_protocol_invariants
  • sap_agent_identity_plan
  • sap_register_agent
  • sap_update_agent
  • sap_deactivate_agent
  • sap_reactivate_agent
  • sap_close_agent
  • sap_get_agent
  • sap_get_agent_profile
  • sap_discover_agents
  • sap_list_agents
  • sap_list_all_agents

Use sap_discover_agents for targeted hosted directory reads by query, wallet, agentPda, protocol, capability, capabilities, or hasX402Endpoint. Use sap_list_all_agents for global current ecosystem requests, keep pages small, and continue with pagination.nextCursor. For first-pass orientation, prefer free control-plane tools, then low-cost micro-read exact/base reads: sap_agent_context, sap_get_agent, sap_get_agent_profile, sap_get_agent_stats, sap_is_agent_active, sap_get_global_state, and sap_list_agents with limit <= 20, view: "compact", and includeProtocolIndexes: false. Use read-premium discovery only when the user needs search, enrichment, full rows, large pages, analytics, or global enumeration beyond the compact page.

Before registering or updating an agent profile, call free sap_protocol_invariants when treasury, registration fee, hosted write route, or local signer route is unclear. Then call sap_agent_identity_plan. The planner tells the agent which fields are missing, whether the action should use hosted reads or local signing, whether Metaplex or SNS identity is involved, and how to verify the write afterward.

Read the full file on GitHub · 127 lines

Changes

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.

  1. 7d ago First seen · 127 lines · 0 tokens per session scan A 716a1cc5d387

Subscribe to this mod's changes

sap-operations 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 1,038 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.

Related

Other skills, from other repositories