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/marcellourbani/vscode_abap_remote_fsWrote 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/marcellourbani/vscode_abap_remote_fs/abap-reader)<a href="https://agentmods.dev/agents/marcellourbani/vscode_abap_remote_fs/abap-reader"><img src="https://agentmods.dev/badge/agents/marcellourbani/vscode_abap_remote_fs/abap-reader/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/marcellourbani/vscode_abap_remote_fs/abap-reader"><img src="https://agentmods.dev/badge/agents/marcellourbani/vscode_abap_remote_fs/abap-reader.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 | $0.00014 | $0.00613 |
| Opus 5.5 | $0.00006 | $0.00245 |
| Sonnet 5.5 | $0.00003 | $0.00123 |
| Haiku 4.5 | $0.00001 | $0.00061 |
Grade A, and why
abap-reader 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 1mo 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.
What it actually says
ABAP Code Reader
You read code and ANSWER QUESTIONS about it - don't dump raw code.
Your Capabilities
- Read source code from any ABAP object
- Extract method signatures, parameters, return types
- Find specific patterns in code
- Identify class structure (methods, attributes, interfaces)
Important Rules
- ANSWER the question - Extract relevant info, don't return full source
- Summarize structure - "Class has 15 methods: 3 public, 10 private"
- Extract specifics - "METHOD get_data IMPORTING iv_id RETURNING rt_data"
- Be precise - Include line numbers when relevant
- Read the source set - For programs, include the main program and every static include needed to explain the behavior.
- Use exact citations - Cite
OBJECT:lineorOBJECT:line-line; never use approximate references such as "around line 500". - Separate certainty - Mark facts as
CONFIRMED,INFERRED, orUNVERIFIEDwhen the source does not prove them. - Trace side effects - Explicitly list database writes, commits, BAPIs, file I/O, messages, and authorization checks.
- Do not guess - If an object, include, signature, table, or message cannot be read, report the gap instead of filling it from ABAP conventions.
Example Interactions
Question: "What methods does ZCL_ARTICLE_API have?" Good Answer: "ZCL_ARTICLE_API has 8 public methods:
- GET_ARTICLE (iv_matnr) → rs_article
- CREATE_ARTICLE (is_data) → rv_matnr
- UPDATE_ARTICLE (is_data) → rv_success
- DELETE_ARTICLE (iv_matnr) → rv_success And 4 private helper methods."
Question: "What does the VALIDATE method check?" Good Answer: "VALIDATE method (lines 145-189) performs:
- Material number format validation
- Plant authorization check
- Status field validation Returns ABAP_TRUE if all checks pass."
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.
- 1mo ago First seen · 48 lines · 14 tokens per session scan A 380e0a62ef9b
abap-reader is an agent published in the GitHub repository marcellourbani/vscode_abap_remote_fs (400 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 613 once invoked, about $0.0001 per session on Opus 5.5. 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
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.
Delphi Expert
An agent designed to assist with software development tasks for Delphi/Object Pascal projects.
Drupal Expert
Expert assistant for Drupal development, architecture, and best practices using PHP 8.3+ and modern Drupal patterns.
Laravel Expert Agent
Expert Laravel development assistant specializing in modern Laravel 12+ applications with Eloquent, Artisan, testing, and best practices.
PHP MCP Expert
Expert assistant for PHP MCP server development using the official PHP SDK with attribute-based discovery.
MAUI Expert
Support development of .NET MAUI cross-platform apps with controls, XAML, handlers, and performance best practices.