Getting it into your agent
There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.
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.
[](https://agentmods.dev/skills/gixsy95/abap_wiki/query)<a href="https://agentmods.dev/skills/gixsy95/abap_wiki/query"><img src="https://agentmods.dev/badge/skills/gixsy95/abap_wiki/query.svg" alt="Measured on agentmods" 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 | $0.00080 | $0.00587 |
| Opus 5 | $0.00040 | $0.00293 |
| Sonnet 5 | $0.00016 | $0.00117 |
| Haiku 4.5 | $0.00008 | $0.00059 |
Grade A, and why
query 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 6d 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
Query - querying the knowledge base
Answers technical/functional questions about custom ABAP code using the wiki,
with traceability via [[wikilink]].
Strategy
- Read
abap_wiki/index.mdto identify the relevant areas. - Narrow down via
abap_wiki/_packages/<DEVCLASS>.md. - Open only the necessary object pages (
abap_wiki/<DEVCLASS>/<sap_type>-<NAME>.md), not the entire wiki. - Code details (L1 analysis) are inline in the same object page: scroll through the sections (Summary, Functional scope, Form analysis, Performance, Bug candidates...) and, for mains, "Program structure" (includes) and "Dependencies".
- Synthesize using
[[wikilink]]for every cited object.
You can also query the DB for quick structural queries:
python core/src/tools/pipeline.py progress --json
or read state/exports/progress.json.
MCP extension (<SAP_DEV_SYSTEM> system, read-only)
When the wiki is not enough (missing or L0 page, need current data, drift check,
enriched metadata) you can query the abap-fs server:
- always read-only;
- cite the source explicitly: "according to [[program-X]] it uses MSEG; verified
via MCP
<SAP_DEV_SYSTEM>: also calls MBEW not documented in wiki"; - if you discover inconsistencies (wiki says X, system says Y) report them and propose an update.
Value preservation
- A precise answer of lasting interest -> propose saving it to
output/reports/<topic>-<YYYYMMDD>.md. - Stable knowledge about an object/flow -> propose promotion (L1 analysis via ingest-l1, or the L2 process when available).
Tracking (operational log)
At the end of the query, record the operation in the event log (so it appears in
log.md, the append-only history view - CLAUDE.md §13):
python core/src/tools/pipeline.py log-op --type query --note "<question summary>" [--package <DEVCLASS>]
One concise line, not the full answer. This is write-only on the events table
(no changes to pages or raw/).
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.
- 6d ago First seen · 50 lines · 80 tokens per session scan A 5c322c0f1943
query is a skill published in the GitHub repository Gixsy95/abap_wiki (44 stars, last pushed 5d ago), licensed MIT. It adds 80 tokens to every session and 587 once invoked, about $0.0004 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
link-memory
Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore, forget, or explain local memories through the CLI without requiring MCP.
link-retrieve
Use before answering work that may depend on user memory, project history, source-backed notes, or prior decisions; retrieve compact Link context through the CLI without loading the whole wiki or requiring MCP.
link-health
Use at the start of Link work when readiness is unclear, after installs or upgrades, and before repairs; verify health, inspect interrupted writes, back up, and repair generated indexes without MCP.
link-ingest
Use when raw files are present, source pages look stale, or a user asks to ingest notes into Link; refresh source-backed wiki pages, propose memories, and validate updates through the CLI without MCP.
ingest
Populate the gnosis-mcp knowledge base — from local files, git history, or a crawled website. Handles the full matrix of flags (--force, --prune, --wipe, --embed, --include-crawled) in one place.
eval
Measure retrieval quality on your corpus — Hit@5, MRR, nDCG@10, Precision@5. Thin wrapper around gnosis-mcp eval with regression tracking against a saved baseline, plain-English interpretation, and tuning pointers when numbers look off. Use after every ingest or config change.