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 instructions/marianfoo/sap-api-policy-skill/claude-mdgit clone --depth 1 https://github.com/marianfoo/sap-api-policy-skillWrote 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/instructions/marianfoo/sap-api-policy-skill/claude-md)<a href="https://agentmods.dev/instructions/marianfoo/sap-api-policy-skill/claude-md"><img src="https://agentmods.dev/badge/instructions/marianfoo/sap-api-policy-skill/claude-md.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 | $0.01276 | $0.01276 |
| Opus 5 | $0.00638 | $0.00638 |
| Sonnet 5 | $0.00255 | $0.00255 |
| Haiku 4.5 | $0.00128 | $0.00128 |
Grade A, and why
sap-api-policy-skill CLAUDE.md 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 5d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — sap-api-policy-skill
Guidance for Claude Code (and any agent) working in this repo. End users don't need this — they just install the skill (see README.md).
What this repo is
This repo packages the sap-api-policy-evidence agent skill, distributed via the
npx skills CLI. The skill assesses whether an SAP API
usage scenario aligns with the SAP API Policy v.4.2026a (+ FAQ v1.2) and returns an
evidence-based, sourced, confidence-rated technical assessment — gathering live evidence from SAP
MCP servers.
It is the skill + its test harness + setup docs. It is not the MCP servers themselves — those
live in the separate sap-mcp-servers monorepo (see
MCP_SETUP.md).
The one invariant — never break this
The skill's output is never legal advice, contractual advice, or a final/definitive SAP compliance decision — only an evidence-based technical assessment with a confidence level and SAP-escalation questions. SAP itself declines to publish a binary "compliant / not compliant" decision matrix (FAQ Q49), so a confident yes/no would misrepresent what is knowable. Every report carries the non-legal disclaimer at top and bottom, and legal / commercial / roadmap questions are routed to SAP, not answered. Any change that lets the skill emit an unconditional verdict, drop the disclaimer, or opine on legal/commercial matters is wrong.
Layout
skills/sap-api-policy-evidence/
SKILL.md entry point — loaded into context on trigger. KEEP IT LEAN.
references/ progressive-disclosure detail, read on demand per workflow step:
policy-baseline.md 5 policy clauses, definitions, red flags, scenario rules, endorsed
pathways, SAP-Note examples, FAQ (Q##) anchors
evidence-model.md intake triage, source hierarchy, confidence rubric, ledger fields
tool-playbooks.md per-MCP-server tool calls, runtime self-check, auth-failure handling
report-template.md required report structure + fixed-label rules
inventory-scan-mode.md batch "which of these APIs are allowed?" workflow
agents/openai.yaml Codex integration
evals/evals.json 22 scenario evals (behavioral test suite)
tests/skill_static_checks.py the machine-checkable contract (run this before committing)
MCP_SETUP.md how users wire up the SAP MCP servers + install the skill
README.md public front page
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.
- 5d ago First seen · 95 lines · 1,276 tokens per session scan A 90cb1b107369
sap-api-policy-skill CLAUDE.md is an instructions file published in the GitHub repository marianfoo/sap-api-policy-skill (9 stars, last pushed 3mo ago), licensed MIT. It adds 1,276 tokens to every session, about $0.0064 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 instructions, from other repositories
privacy-kit-cl AGENTS.md
Instructions for Yugoxc/privacy-kit-cl, covering agents.md — guía de integración para una ia, objetivo, paso 0 — detectar el terreno, paso 1 — instalar y configurar and paso 2 — implementar el store.
mcp-eu-compliance AGENTS.md
AGENTS.md instructions for matematicsolutions/mcp-eu-compliance, covering agents.md - mcp-eu-compliance, project purpose, matematic context (hard constraints), mcp tools (tools contract) and build and test.
ue-official-mcp CLAUDE.md
Instructions for tc-imba/ue-official-mcp, covering claude.md, what this is, core invariants — don't break these, common commands and architecture pointers.
legal-audit-de AGENTS.md
AGENTS.md instructions for FutureRootsDE/legal-audit-de, covering agents.md — legal-audit-de, haftungsausschluss — keine rechtsberatung, was macht das plugin?, plattform-layouts and commands / prompts.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.