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 marcellourbani/vscode_abap_remote_fs --skill repository-assisted-applygit 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/skills/marcellourbani/vscode_abap_remote_fs/repository-assisted-apply)<a href="https://agentmods.dev/skills/marcellourbani/vscode_abap_remote_fs/repository-assisted-apply"><img src="https://agentmods.dev/badge/skills/marcellourbani/vscode_abap_remote_fs/repository-assisted-apply/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/marcellourbani/vscode_abap_remote_fs/repository-assisted-apply"><img src="https://agentmods.dev/badge/skills/marcellourbani/vscode_abap_remote_fs/repository-assisted-apply.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 | $0.00057 | $0.02067 |
| Opus 5.5 | $0.00023 | $0.00827 |
| Sonnet 5.5 | $0.00011 | $0.00413 |
| Haiku 4.5 | $0.00006 | $0.00207 |
Grade A, and why
repository-assisted-apply 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 yesterday.
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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Assisted Apply
Use this skill only for the Copilot-assisted apply phase of an ABAP FS repository-comparison workflow. Do not use its apply or activation-record operations for ordinary ABAP editing.
Repository assisted apply propagates reviewed raw source between live SAP systems, saves inactive code through CTS transport handling, and can activate executable repository objects. A wrong object, stale review, guessed transport, incomplete activation set, or unintended retry can overwrite pending work or affect unrelated code. The rules in this skill are authorization and safety boundaries: follow them exactly, fail closed on missing evidence, and return control to the user instead of guessing.
The user owns all authorization boundaries:
- enabling Copilot-assisted mode;
- selecting and saving the exact eligible objects;
- approving an existing transport request, a new-request description, or local handling;
- approving each tool confirmation.
Copilot reviews and orchestrates one selected object at a time. It never chooses objects or transports.
Preconditions
Before any per-object work:
- The comparison and assisted-apply plan must already exist.
- The workflow must currently be in Copilot-assisted mode with recorded user consent.
- The user must have saved the allowed object selection in the workflow UI.
- The exact object must be pending and eligible.
Use abapfs_get_repository_workflow with the smallest required includes. Read
assistedApplyObjects to confirm selection and state; use diff with one exact objectKey for a
bounded raw or formatted review. Never request unbounded repository source.
Parent-agent orchestration
Prefer delegating execution to abap-repository-assisted-apply when that enabled subagent is
available. One invocation handles exactly one table object.
Before delegation, the parent agent must:
- identify one exact
workflowIdand one exact savedobjectKey; - obtain current target transport status when necessary;
- explain any existing lock to the user;
- collect the user's exact transport direction;
- pass only that one object and direction to the subagent.
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.
- yesterday First seen · 188 lines · 57 tokens per session scan A 5139acbdaca3
repository-assisted-apply is a skill published in the GitHub repository marcellourbani/vscode_abap_remote_fs (399 stars, last pushed yesterday), licensed MIT. It adds 57 tokens to every session and 2,067 once invoked, about $0.0002 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 2026-10-17.
Other skills, from other repositories
oss-submit-pr
Submit a pull request following the repo's contribution guidelines. Reviews the diff, checks for common rejection reasons, and helps the user write their own PR description. The LLM reviews. the user writes. Use when implementation is complete and tests pass. Not for responding to review comments after the PR is open.…
oss-post-pr
Handle PR review feedback - understand reviewer comments, research their concerns, and help the user address them. The LLM explains what reviewers want and why; the user decides how to respond and writes the code. Use when you receive review comments on a submitted PR. Not for opening the PR in the first place, which…
sap-git
Install-free, read-only git backend for custom ABAP: gives Z code the PR-style review, blame, readable TR diffs, and whole-package-on-disk that abapGit would — without installing abapGit (often politically impossible on customer systems) and without ever writing to SAP. snapshot serializes a PACKAGE / TR / object-list…
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.