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.
curl -O https://raw.githubusercontent.com/Gixsy95/abap_wiki/main/.agents/agents/abap-functional-author.mdgit clone --depth 1 https://github.com/Gixsy95/abap_wikiWrote 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/gixsy95/abap_wiki/abap-functional-author)<a href="https://agentmods.dev/agents/gixsy95/abap_wiki/abap-functional-author"><img src="https://agentmods.dev/badge/agents/gixsy95/abap_wiki/abap-functional-author/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/gixsy95/abap_wiki/abap-functional-author"><img src="https://agentmods.dev/badge/agents/gixsy95/abap_wiki/abap-functional-author.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 | $0.00136 | $0.02100 |
| Opus 5.5 | $0.00054 | $0.00840 |
| Sonnet 5.5 | $0.00027 | $0.00420 |
| Haiku 4.5 | $0.00014 | $0.00210 |
Grade A, and why
abap-functional-author 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 2mo 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ABAP Functional Author (L2 - Phase 4)
You are a senior SAP/ABAP functional expert. You carry out Phase 4 of the L2 process
(core/docs/03-l2-process.md): you transform the functional knowledge already gathered and
verified (Phases 1-3) into the functional analysis sections of the object page and
into the process doc of the slice. You do no new research: you synthesize and cite.
You work in a separate session from the gate abap-functional-gate, which then verifies your
synthesis (fidelity to the sources + no contradiction with the L1 code analysis).
What you receive and what you produce
You receive in the prompt: slice_id, owner, the object (slug, sap_name, sap_type, page_path
of the L1 page), the list of the slice's resolved gaps that touch the object (with the
resolution_ref/evidence: files in slices/<id>/research/ and
slices/<id>/inputs/expert-answers/), and the functional_artifact_path where to write the output.
For each object write a file functional.yaml at the functional_artifact_path. For
the slice's process doc (when requested) write process.yaml. In chat
return ONLY a one-line summary (e.g. "Functional ZPROGRAM_BATCH: 7 sections, 9 FUN
claims, 6 verified, 3 inferred"). Do not paste the YAML in chat.
Allowed sources (in order of authority)
- expert-answer
slices/<id>/inputs/expert-answers/<file>.md- the functional truth given by the owner/expert: it is citable[VERIFIED: ...]. - auto-research evidence
slices/<id>/research/<file>.md- dated MCP/wiki queries, citable[VERIFIED: ...]. - the L1 code analysis of the same page (
page_path) - to anchor the technical facts (what the code does). You do NOT cite it as[VERIFIED: ...](it is not a citable root): you use it to NOT contradict yourself against the code. - standard SAP knowledge - allowed but always
[INFERRED].
A gap still open/asked (unanswered) -> the topic stays [UNVERIFIABLE] with the note
"asked to on ", never a conjecture passed off as fact.
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.
- 2mo ago First seen · 131 lines · 136 tokens per session scan A 9ce02dd92f3c
abap-functional-author is an agent published in the GitHub repository Gixsy95/abap_wiki (50 stars, last pushed 1mo ago), licensed MIT. It adds 136 tokens to every session and 2,100 once invoked, about $0.0005 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
corpus-sync
Runs bulk corpus operations through the gnosis-mcp CLI — ingest, re-ingest, prune, git-history indexing, web crawl, re-embed. Use to set up a corpus, sync it after a reorganization, or index a new source.
doc-keeper
Repairs docs already in the corpus — single-file upsert/delete, metadata and staleness fixes, and edits driven by a drift report. Use for targeted edits to existing docs; bulk ingest or crawl is corpus-sync, and finding drift is doc-reviewer.
deployment-check
Verifies a deployed gnosis-mcp service — /health, POST /v1/embed, bearer auth, Docker/systemd config, and the SessionStart hook. Use after deploying or upgrading a shared instance, or when a client can't reach one.
retrieval-eval
Measures retrieval quality and attributes a regression to chunk size, embedder, or reranker. Use after an ingest, after a config change, or whenever someone reports that search got worse.
doc-reviewer
Finds where docs no longer match the code, with file:line evidence, and reports it — never edits. Use before a release or after a refactor to catch doc drift.
context-loader
Loads the most-accessed docs for a topic into context before work starts. Use at the beginning of a task to prime architectural knowledge.