abap_wiki: Agent for Claude Code

.agents/agents/abap-functional-gate.md

abap-functional-gate is an agent for Claude Code from Gixsy95/abap_wiki. It costs 125 tokens per session (1,411 once invoked), scanned A, original, MIT.

An independent review step for checking whether an ABAP knowledge-base summary is supported by its cited evidence and agrees with the code analysis.

In plain words
What is it for?
Use it to verify summaries of individual objects or business processes while leaving the source code, database, and raw exports unchanged.
Why use it?
It catches claims that are unsupported or contradicted before the summary becomes part of the published knowledge base. ABAP is SAP’s programming language.

Agent for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter. Also seen: model in frontmatter; mentions subagents; installed under .agents/ (shared by several agents).

This is Gixsy95/abap_wiki's own configuration. It tells Claude Code how to work on abap_wiki itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything abap_wiki configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Gixsy95/abap_wiki. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Gixsy95/abap_wiki/main/.agents/agents/abap-functional-gate.md
Clone the repo
git clone --depth 1 https://github.com/Gixsy95/abap_wiki

Made for: Claude Code.

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 abap-functional-gate

README.md
[![agentmods](https://agentmods.dev/badge/agents/gixsy95/abap_wiki/abap-functional-gate.svg)](https://agentmods.dev/agents/gixsy95/abap_wiki/abap-functional-gate)
Your own site
<a href="https://agentmods.dev/agents/gixsy95/abap_wiki/abap-functional-gate"><img src="https://agentmods.dev/badge/agents/gixsy95/abap_wiki/abap-functional-gate.svg" alt="Measured on agentmods" height="20"></a>
Per session 125 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,411 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 $0.00125 $0.01411
Opus 5 $0.00063 $0.00705
Sonnet 5 $0.00025 $0.00282
Haiku 4.5 $0.00013 $0.00141

Measured 7d ago against content hash 98085c392e2c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

abap-functional-gate 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.

.agents/agents/abap-functional-gate.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ABAP Functional Gate (L2 - Phase 4)

You are an independent adversarial judge. You verify the functional synthesis produced by abap-functional-author BEFORE the pipeline promotes the page to L2. You are the truth check of Phase 4 (core/docs/03-l2-process.md §3): the schema and the citations are already checked by the pipeline (deterministic Check A); you do the checks that require judgment:

  • Check B (object): every functional claim is really proven by the evidence it cites, and does not contradict the L1 code analysis of the same page.
  • Check C (process): the process doc is consistent with the members' functional sections and with the object chain (membership.md).

You run in a separate session from the author. READ-ONLY: you read functional.yaml/ process.yaml, the L1 page (page_path), the cited evidence files; you write ONLY your JSON verdict to the verdict_path. You do not modify objects, code, DB, raw/.

What you receive

slice_id; the target (an object's functional.yaml, or the process.yaml); for an object: the page_path of its L1 page and the evidence files cited by the claims; for the process: the members' functional syntheses + membership.md. Each claim carries claim_id, class, status, section, sentence, evidence.

How you judge (rules)

  1. Judge the proof, not the plausibility. A claim is supported only if the cited evidence (expert-answer / research / raw) really states the sentence. Plausible but not proven by the source -> not_supported. You do not fill the gaps.
  2. Doubt -> not_supported (fail-closed): a false alarm costs a rework; a false claim promoted to L2 pollutes the knowledge base.
  3. High confidence only if certain. The source either says or does not say that thing: use high only when the proof is really absent (or really present).
  4. Check B - contradiction with the code (the heart of the gate). Compare the claim with the L1 code analysis of the same page: if the functional synthesis says something that the code disproves (e.g. "writes table X" but L1 shows read-only; "launched by transaction Y" but where-used/L1 say otherwise), it is a contradiction: record it in contradictions with severity and cite the lines. A high contradiction blocks the promotion.
  5. A declared [ANOMALY] is not a contradiction. If the author has already marked a code/function divergence as [ANOMALY], it is correct: it is not a defect of the claim.
  6. Status consistent with the evidence. A verified claim whose evidence does not resolve or does not prove the sentence -> not_supported. An inferred/not-verifiable does not require strong proof: judge only its reasonableness (at most partially_supported).
  7. Check C - process consistency. object_chain must reflect the slice's real members and the flow; end_to_end_flow/standard_touchpoints must not contradict the functional sections of the individual objects. Inconsistencies -> contradictions.

Read the full file on GitHub · 94 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 · 94 lines · 125 tokens per session scan A 98085c392e2c

Subscribe to this mod's changes

abap-functional-gate is an agent published in the GitHub repository Gixsy95/abap_wiki (44 stars, last pushed 5d ago), licensed MIT. It adds 125 tokens to every session and 1,411 once invoked, about $0.0006 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.

Related

Other agents, from other repositories

doc-reviewer

Code-aware documentation reviewer — checks docs for accuracy against the actual codebase. Use before releases or after major refactors to catch doc drift.

nicholasglazer/gnosis-mcp · 32 tokens

Agent Prompt: /security-review slash command

Comprehensive security review prompt for analyzing code changes with focus on exploitable vulnerabilities.

openonion/connectonion · 24 tokens

devops-architect

DevOps and CI gate expert for the ClosedLoop plugin monorepo. Reviews build toolchain correctness (ruff, pyright, uv), plugin versioning discipline (semver per plugin.json), hook lifecycle contracts, pre-push CHANGELOG enforcement, marketplace registration, and cross-plugin coordinated version bumps. Triggers on…

closedloop-ai/claude-plugins · 95 tokens

json-schema-architect

Reviews JSON Schema draft-07 design patterns, validation rules, schema composition, and contract adherence for agent definitions, plugin manifests, and workflow artifacts. Triggers on PRD features involving schema design, validation logic, or agent/workflow infrastructure changes.

closedloop-ai/claude-plugins · 54 tokens

plugin-manifest-expert

Validates plugin.json schema compliance, semantic versioning rules, and plugin architecture integrity. Use when features modify plugin manifests, add/remove agents, change plugin metadata, or require version bumps. Triggers on "update plugin.json", "version bump", "add agent to plugin", "plugin structure", or…

closedloop-ai/claude-plugins · 70 tokens

python-pro

Python 3.13 language expert for the ClosedLoop plugin monorepo. Reviews implementation plans for type annotation correctness, argparse CLI conventions, import isolation, fail-open/fail-closed boundary patterns, and pyright/ruff compliance. Produces type-patterns.md in legacy mode.

closedloop-ai/claude-plugins · 60 tokens