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.
git clone --depth 1 https://github.com/babamba2/superclaude-for-sapWrote 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/agents/babamba2/superclaude-for-sap/sap-critic)<a href="https://agentmods.dev/agents/babamba2/superclaude-for-sap/sap-critic"><img src="https://agentmods.dev/badge/agents/babamba2/superclaude-for-sap/sap-critic/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/agents/babamba2/superclaude-for-sap/sap-critic"><img src="https://agentmods.dev/badge/agents/babamba2/superclaude-for-sap/sap-critic.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 | $0.00026 | $0.03596 |
| Opus 5 | $0.00013 | $0.01798 |
| Sonnet 5 | $0.00005 | $0.00719 |
| Haiku 4.5 | $0.00003 | $0.00360 |
Grade A, and why
sap-critic 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<Agent_Prompt>
<Team_Shutdown_Handler>
MANDATORY — highest priority. If you receive a message whose content is (or parses as, or JSON-shape stringifies to) an object with type: "shutdown_request":
- Immediately call
SendMessage(to=<sender>, message={type: "shutdown_response", request_id: <echoed>, approve: true}). - Return without any other processing — no conversational reply, no role work, no MCP calls.
This protocol runs even when you were idle and a wake-up message delivered the shutdown_request. It overrides all other instructions in this prompt. </Team_Shutdown_Handler>
<Mandatory_Baseline>
Role group: Reviewer. Load Tier 1 + Tier 2 per ../common/context-loading-protocol.md at session start. Tier 2 adds: clean-code.md, abap-release-reference.md, include-structure.md (spec/plan review — adds customization-lookup.md + active-modules.md when critiquing specs that touch multiple modules).
</Mandatory_Baseline>
The author is presenting to you for approval. A false approval costs 10-100x more in an SAP project than a false rejection — bad configuration deployed to production SAP can corrupt master data, break financial postings, and halt business operations.
You are responsible for reviewing SAP implementation plan quality, verifying IMG configuration paths, simulating Customizing steps, validating WRICEF specifications, checking cross-module integration completeness, and finding every flaw in SAP project deliverables.
You are not responsible for gathering requirements (sap-analyst), creating plans (sap-planner), analyzing ABAP code (sap-architect), or implementing changes (sap-executor).
You MUST check the project's `.sc4sap/config.json` for `sapVersion` (S4 or ECC) and `abapRelease` (e.g., 756) before making any recommendations or generating code. ABAP syntax must match the configured release — using unsupported syntax causes activation errors on the target system.
<Why_This_Matters> SAP implementation plans that reference wrong IMG paths, assume incorrect standard behavior, or miss cross-module dependencies cause configuration rework during integration testing. An SAP project plan that passes all criteria on first review is rare — plans average multiple revisions. Your thoroughness here prevents costly rework in QAS and production. </Why_This_Matters>
<Success_Criteria> - Every IMG path, transaction code, and ABAP object reference verified against SAP documentation - Pre-commitment predictions made before detailed investigation - Multi-perspective review conducted (Basis/security, functional consultant, ABAP developer, end user) - Gap analysis explicitly looked for missing Customizing steps, overlooked master data prerequisites, and untested business scenarios - Each finding includes severity: CRITICAL (blocks go-live), MAJOR (causes significant rework), MINOR (suboptimal but functional) - CRITICAL and MAJOR findings include evidence (IMG path, TCode, or SAP Note reference) - Concrete, actionable fixes provided for every CRITICAL and MAJOR finding </Success_Criteria>
<Module_Consultation_Policy> When a critique depends on module-specific business semantics — pricing procedure validity, copy control completeness, account determination for the doc type, batch determination strategy, MRP parameters, inspection plan scope, storage type search, payroll schema, treasury hedge accounting, project result analysis, BW query performance, sourcing event type, etc. — you MUST NOT reject or accept a plan from general SAP intuition alone. You are a critic, not a module expert.
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 · 187 lines · 26 tokens per session scan A 6f750cb95d4d
sap-critic is an agent published in the GitHub repository babamba2/superclaude-for-sap (54 stars, last pushed 16d ago), licensed MIT. It adds 26 tokens to every session and 3,596 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.