concur

concur is a skill for Claude Code from vigneshbarani24/sap-superpowers. It costs 56 tokens per session (3,094 once invoked), scanned A, original, MIT.

A set of guidance for SAP Concur, a platform for managing employee expenses, business travel, invoices, requests, receipts, and approvals. It also covers posting Concur transactions into SAP financial accounting.

In plain words
What is it for?
Use it to configure expense and travel workflows, receipt rules, invoice processing, audit checks, approvals, and Concur API or S/4HANA integrations.
Why use it?
It helps prevent policy violations, missing receipts, incorrect expense postings, and approval or audit gaps.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: positional $N argument.

Part of the sap-superpowers plugin — 61 skills, 8 commands, 15 agents, 5 hooks shipped together

Good fit Use it to configure expense and travel workflows, receipt rules, invoice processing, audit checks, approvals, and Concur API or S/4HANA integrations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vigneshbarani24/sap-superpowers/concur
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 vigneshbarani24/sap-superpowers --skill concur
Clone the repo
git clone --depth 1 https://github.com/vigneshbarani24/sap-superpowers

Made for: Claude Code.

Or install sap-superpowers, the plugin that ships this one along with the rest of its 61 skills, 8 commands, 15 agents, 5 hooks.

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 concur

README.md
[![agentmods](https://agentmods.dev/badge/skills/vigneshbarani24/sap-superpowers/concur/github.svg)](https://agentmods.dev/skills/vigneshbarani24/sap-superpowers/concur)
Your own site
<a href="https://agentmods.dev/skills/vigneshbarani24/sap-superpowers/concur"><img src="https://agentmods.dev/badge/skills/vigneshbarani24/sap-superpowers/concur/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.

agentmods 80×15 button for concur

Your own site · 80×15
<a href="https://agentmods.dev/skills/vigneshbarani24/sap-superpowers/concur"><img src="https://agentmods.dev/badge/skills/vigneshbarani24/sap-superpowers/concur.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,094 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 $0.00056 $0.03094
Opus 5 $0.00028 $0.01547
Sonnet 5 $0.00011 $0.00619
Haiku 4.5 $0.00006 $0.00309

Measured 5d ago against content hash 63dbe6fd02c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

concur 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.

skills/modules/concur/SKILL.md · 293 lines

How it starts

The opening of the file, as written. The whole thing — 293 lines — stays where its author put it; the contents beside it link to each section on GitHub.

SAP Concur

This skill enforces correct Concur implementation practices, ensuring that audit rules are configured before go-live, expense policies are fully defined for all categories, and integration posting to FI is validated with every expense type — because an expense report that posts incorrectly to the general ledger is worse than one that does not post at all.

Content Routing

Topic Section
Concur Expense Concur Expense
Concur Travel Concur Travel
Concur Invoice Concur Invoice
Concur Request (pre-approval) Concur Request
Expense policy configuration Expense Policy Configuration
Receipt management Receipt Management
Approval workflows Approval Workflows
Integration with S/4HANA FI Integration with S/4HANA
Audit rules and compliance Audit Rules and Compliance
Concur APIs Concur APIs

Iron Laws

  1. ALWAYS CONFIGURE AUDIT RULES BEFORE GO-LIVE. Audit rules are the automated policy enforcement layer. Going live without audit rules means every expense is trusted at face value. Configure duplicate detection, receipt requirement thresholds, per diem limits, and policy violation flags before the first expense report is submitted.
  2. NEVER SKIP POLICY CONFIGURATION FOR EXPENSE CATEGORIES. Every expense type (meals, lodging, mileage, airfare, ground transport, entertainment) needs explicit policy limits, receipt requirements, and approval routing. An undefined expense category is an uncontrolled spending category.
  3. ALWAYS TEST INTEGRATION POSTING TO FI WITH ALL EXPENSE TYPES. Each expense type maps to a different GL account, cost center, and possibly WBS element or internal order. Test every expense type end-to-end: expense creation -> approval -> extraction -> SAE posting -> FI document verification. One missing mapping means that expense type fails in production.
  4. NEVER ALLOW EXPENSE SUBMISSION WITHOUT RECEIPT FOR AMOUNTS ABOVE THRESHOLD. Receipt-less expense claims above the configured threshold (commonly $25-$75 per jurisdiction) are audit red flags. Configure receipt-required thresholds per expense type and enforce them with hard stops, not warnings.
  5. ALWAYS CONFIGURE DELEGATION RULES FOR APPROVERS. Approvers travel, get sick, and go on vacation. Without delegation rules, expense reports queue indefinitely. Configure delegation, escalation timeouts, and backup approvers for every approval step.

Read the full file on GitHub · 293 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. 5d ago First seen · 293 lines · 56 tokens per session scan A 63dbe6fd02c4

Subscribe to this mod's changes

concur is a skill published in the GitHub repository vigneshbarani24/sap-superpowers (9 stars, last pushed 17d ago), licensed MIT. It adds 56 tokens to every session and 3,094 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 2026-09-03.