An L1 analysis workflow for the abapwiki knowledge base. L1 records what ABAP code does, then checks each analysis against cited source lines before accepting it.

Use it to process batches of code objects, resume interrupted work, run analysis and review agents, and promote verified results from basic stubs to detailed pages.

The separate review step and fail-closed rule help prevent unsupported code explanations or false dependencies from entering the knowledge base.

How Gixsy95/abap_wiki configures Claude Code and Codex

Reuse

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.

Copy the file

curl -O https://raw.githubusercontent.com/Gixsy95/abap_wiki/main/.agents/skills/ingest-l1/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/Gixsy95/abap_wiki

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gixsy95/abap_wiki/ingest-l1/github.svg)](https://agentmods.dev/skills/gixsy95/abap_wiki/ingest-l1)

Your own site

<a href="https://agentmods.dev/skills/gixsy95/abap_wiki/ingest-l1"><img src="https://agentmods.dev/badge/skills/gixsy95/abap_wiki/ingest-l1/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gixsy95/abap_wiki/ingest-l1"><img src="https://agentmods.dev/badge/skills/gixsy95/abap_wiki/ingest-l1.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,610 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

SkillSpector: 1 finding, up to low

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

low Excessive Agency · line 10
Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.

Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00091	$0.01610
Opus 5	$0.00046	$0.00805
Sonnet 5	$0.00018	$0.00322
Haiku 4.5	$0.00009	$0.00161

Measured 11d ago against content hash c62af1db3725, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ingest-l1 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 11d 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.

.agents/skills/ingest-l1/SKILL.md · 108 lines

How it starts

The opening of the file, as written. The whole thing — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ingest L1 - code analysis with adversarial gate

Promotes objects from L0 stub to L1 page with verified code analysis. The cycle is driven by you (main agent): you invoke sub-agents via the Task tool, the scripts handle everything else (state, validation, gate, page writing).

Architecture (see core/docs/01-pipeline-l0-l1.md and 02-adversarial-gate.md):

author = sub-agent abap-analyzer (raw-only): reads the source and writes output/runs/<run>/<task>/author.yaml (anchored claims + dependencies).
deepcheck = sub-agent abap-deepcheck (different model, separate session): verifies that every claim is demonstrated by the cited lines and every dependency is real. Writes deepcheck.json.
gate fail-closed: no page is promoted without a valid, fresh verdict with full coverage.

Batch cycle

Generate run_id = run-<timestamp> and batch_id = b-<timestamp> at the start of each round.

Recover (always, at the start - resumes interrupted tasks without repeating work):
```
python core/src/tools/pipeline.py recover
```
Claim author (10-15 per batch):
```
python core/src/tools/pipeline.py claim --kind l1_author --limit 12 --worker <run_id>
```
Returns JSON with the tasks. If empty, skip to step 4; if empty there too, the loop is done.
Fan-out author IN PARALLEL: for each task one Task(subagent_type="abap-analyzer", ...) passing in the prompt sap_name, sap_type, devclass, raw_source_path and artifact_path = output/runs/<run_id>/<task_id>/author.yaml. On return from each:
```
python core/src/tools/pipeline.py submit-author --task <task_id> --run <run_id> --batch <batch_id>
```

Claim deepcheck and fan-out IN PARALLEL of the judge (separate session):

python core/src/tools/pipeline.py claim --kind l1_deepcheck --limit 12 --worker <run_id>

For each task Task(subagent_type="abap-deepcheck", ...) with the prompt and verdict_path as indicated. On return:

python core/src/tools/pipeline.py submit-verdict --task <task_id> --run <run_id> --batch <batch_id>

Apply (ACCEPT only; idempotent):

python core/src/tools/pipeline.py apply --run <run_id> --batch <batch_id>

Project + commit:

python core/src/tools/pipeline.py project
python core/src/tools/pipeline.py export-excel
python core/src/tools/pipeline.py git-commit --message "ingest L1 batch <batch_id>" --batch <batch_id>

Progress and decide whether to continue:

python core/src/tools/pipeline.py progress --json

Read the full file on GitHub · 108 lines

Changes

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.

11d ago First seen · 108 lines · 91 tokens per session scan A c62af1db3725

Subscribe to this mod's changes

ingest-l1 is a skill published in the GitHub repository Gixsy95/abap_wiki (44 stars, last pushed 3d ago), licensed MIT. It adds 91 tokens to every session and 1,610 once invoked, about $0.0005 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.

Data and AI LLM Research abap agentic-ai documentation knowledge-base markdown

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.

nicholasglazer/gnosis-mcp · 54 tokens

setup

First-time setup wizard for Gnosis MCP. Install, init the database, ingest a docs folder, wire your editor — in that order.

nicholasglazer/gnosis-mcp · 30 tokens

tune

Find the chunk-size and retrieval config that maximizes quality on YOUR corpus. Sweeps chunk sizes, runs a golden-query set, reports nDCG / MRR / Hit@5. Use after first ingest or whenever your corpus changes shape significantly.

nicholasglazer/gnosis-mcp · 53 tokens

accreta-setup

Set up an accreta knowledge base over a corpus — pick a preset, write the config and a source declaration, generate the constitution, wire up MCP, and verify the first ingest. Use when someone wants an agent-maintained knowledge base with provenance and drift detection over a codebase, a document collection, or a…

francescofioredev/accreta · 100 tokens

neuron-test-engineer

Write tests for Neuron AI agents, RAG systems, workflows, and tools using the built-in testing utilities. Use this skill when the user mentions testing agents, writing unit tests, mocking AI providers, testing tool execution, verifying RAG retrieval, testing workflow behavior, or creating test cases for Neuron AI…

neuron-core/neuron-ai · 94 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

abap_wiki: Skill for Claude Code