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 babamba2/superclaude-for-sap --skill trust-sessiongit 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/skills/babamba2/superclaude-for-sap/trust-session)<a href="https://agentmods.dev/skills/babamba2/superclaude-for-sap/trust-session"><img src="https://agentmods.dev/badge/skills/babamba2/superclaude-for-sap/trust-session/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/babamba2/superclaude-for-sap/trust-session"><img src="https://agentmods.dev/badge/skills/babamba2/superclaude-for-sap/trust-session.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 3 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 16 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 68 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 81 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 89 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 105 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 6 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00109 | $0.02344 |
| Opus 5 | $0.00055 | $0.01172 |
| Sonnet 5 | $0.00022 | $0.00469 |
| Haiku 4.5 | $0.00011 | $0.00234 |
Grade A, and why
sc4sap:trust-session 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SC4SAP Trust Session (Internal-Only)
Session-scoped permission bootstrap for automated pipelines. When a long-running parent skill enters its automated phases, sub-agent dispatch (Agent/Task) and .sc4sap/ state-file writes would otherwise trigger permission prompts. This skill pre-grants those so the parent pipeline proceeds uninterrupted.
⚠️ This skill is NOT user-facing. It exists only as a sub-routine of other skills. Direct /sc4sap:trust-session invocation by the user is rejected — see <Standalone_Invocation_Refusal> below.
<Permission_Model_Note>
SAP MCP handler permissions are NOT managed by this skill anymore. They are auto-approved at call time by the permission-approver PreToolUse hook (scripts/permission-approver.mjs, wired in hooks/hooks.json), which returns permissionDecision: "allow" for every mcp__plugin_sc4sap_sap__* / mcp__mcp-abap-adt__* tool except the two row-data extraction tools (GetTableContents, GetSqlQuery), which fall through to normal prompting plus the block-forbidden-tables safeguard. The hook runs in BOTH the main thread and sub-agents, regardless of session permission mode — this replaces the former settings.local.json MCP enumeration and the deprecated mode: "dontAsk" Agent-dispatch parameter (ignored by current Claude Code; sub-agents now inherit the parent session's permission mode). trust-session therefore only handles the NON-MCP grants below.
</Permission_Model_Note>
<Response_Prefix>
Every response triggered by this skill MUST begin with [Model: <main-model> · Dispatched: <sub-summary>] per ../../common/model-routing-rule.md § Response Prefix Convention.
</Response_Prefix>
<Standalone_Invocation_Refusal> MANDATORY gate — runs as Step 0 before any file write.
Detect whether this skill is being invoked standalone or by a parent skill:
- Parent skill present: the invocation is chained from
/sc4sap:create-program,/sc4sap:setup,/sc4sap:analyze-cbo-obj,/sc4sap:analyze-code,/sc4sap:analyze-symptom, or/sc4sap:create-object. The caller passesparent_skill={name}as the first argument OR the invocation appears inside another skill's execution trace in the current turn. - Standalone (no parent): user typed
/sc4sap:trust-sessiondirectly, or the arguments do not identify a known parent.
On standalone invocation, refuse and redirect:
⚠️ /sc4sap:trust-session is an internal-only skill. Direct invocation is not allowed.
To grant session-wide permissions for an automated pipeline, run one of the following
parent skills instead (each auto-invokes trust-session at entry):
• /sc4sap:create-program — program creation pipeline (invokes at Phase 1)
• /sc4sap:create-object — single object creation
• /sc4sap:analyze-cbo-obj — CBO package inventory walk
• /sc4sap:analyze-code — code review
• /sc4sap:analyze-symptom — dump / error root-cause analysis
→ A separate trust-session run is unnecessary — the parent skill handles it for you.
After printing the message, STOP. Do NOT modify .claude/settings.local.json. Do NOT write .sc4sap/session-trust.log.
</Standalone_Invocation_Refusal>
<Use_When>
- Called automatically as Phase 0 / entry step of a parent skill (see list above)
- Parent skill passes
parent_skill={name}argument to identify itself </Use_When>
<Do_Not_Use_When>
- User types
/sc4sap:trust-sessiondirectly → refuse per<Standalone_Invocation_Refusal> - Running on a production SAP system without change authorization </Do_Not_Use_When>
<What_This_Skill_Does>
Single-layer, non-MCP permission grant written to .claude/settings.local.json → permissions.allow (project-local, persists). Scope policy: sub-agent dispatch + .sc4sap/ state I/O only. SAP MCP is handled by the hook; everything else stays prompt-gated.
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 · 126 lines · 109 tokens per session scan A c3aab4e7c235
sc4sap:trust-session is a skill published in the GitHub repository babamba2/superclaude-for-sap (54 stars, last pushed 16d ago), licensed MIT. It adds 109 tokens to every session and 2,344 once invoked, about $0.0005 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 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…