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/skills/ingest-l0/SKILL.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/skills/gixsy95/abap_wiki/ingest-l0)<a href="https://agentmods.dev/skills/gixsy95/abap_wiki/ingest-l0"><img src="https://agentmods.dev/badge/skills/gixsy95/abap_wiki/ingest-l0/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/gixsy95/abap_wiki/ingest-l0"><img src="https://agentmods.dev/badge/skills/gixsy95/abap_wiki/ingest-l0.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00064 | $0.00643 |
| Opus 5 | $0.00032 | $0.00321 |
| Sonnet 5 | $0.00013 | $0.00129 |
| Haiku 4.5 | $0.00006 | $0.00064 |
Grade A, and why
ingest-l0 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 12d 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ingest L0 - stub bootstrap from TADIR
Creates (or updates) the L0 stub for every custom object in the TADIR. Everything is
deterministic: no sub-agents, parallelism via devclass partitioning.
State lives in state/abap_wiki.db (see core/docs/01-pipeline-l0-l1.md).
When to use it
- First-time initialization of the repo (empty DB).
- Arrival of a new export
raw/tadir/TADIR_Z_<YYYYMMDD>.XLSX.
Procedure
Shortcut:
python core/src/tools/pipeline.py l0-runruns steps 1-6 as a single deterministic command (newest TADIR inraw/tadir/or--file). The step-by-step procedure below remains the reference for diagnostics.
All commands must be run from the repo root with the venv active.
- Initialize the schema (idempotent):
python core/src/tools/pipeline.py init-db - Import the TADIR (dtype=str, excludes objects already removed from the L1 queue):
python core/src/tools/pipeline.py import-tadir --file raw/tadir/<most recent TADIR>.XLSX - Resolve sources (unique in-memory index, deterministic hash):
python core/src/tools/pipeline.py resolve-sources - Create L0 stubs (all, or by devclass partition in parallel across multiple sessions):
Idempotent: re-running on an already-processed package is a no-op.python core/src/tools/pipeline.py ingest-l0 # all python core/src/tools/pipeline.py ingest-l0 --partition ZPACKAGE # one package - Enqueue L1 (only analyzable types with available source):
python core/src/tools/pipeline.py enqueue-l1 - Verify and commit:
python core/src/tools/pipeline.py progress python core/src/tools/pipeline.py export-excel python core/src/tools/pipeline.py git-commit --message "ingest L0: <export>"
Rules
- Never modify
raw/(only the user stages it when updating the export). - Indexes (
abap_wiki/_packages/,abap_wiki/index.md) are regenerated from queries: do not edit them manually. - If unknown TADIR types appear they are mapped to
tadir-<x>and listed inoutput/reports/unknown-tadir-types.md(non-blocking).
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.
- 12d ago First seen · 58 lines · 64 tokens per session scan A fcdbf9158a01
ingest-l0 is a skill published in the GitHub repository Gixsy95/abap_wiki (44 stars, last pushed 4d ago), licensed MIT. It adds 64 tokens to every session and 643 once invoked, about $0.0003 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.
eval
Measure retrieval quality — Hit@5, MRR, Precision@5 on a fixed fixture set, or Hit@5/MRR/nDCG@10 on your own corpus via the real-corpus benchmark. Regression tracking against a saved baseline, plain-English interpretation, and tuning pointers when numbers look off. Use after every ingest or config change.
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.