slice-init

slice-init is a skill for Claude Code, Codex from Gixsy95/abap_wiki. It costs 86 tokens per session (919 once invoked), scanned A, original, MIT.

A workflow for starting an L2 slice in the abapwiki knowledge base. An L2 slice is a documented business process, and its members are found from related code using a dependency graph.

In plain words
What is it for?
Use it to choose entry points, name the responsible owner, create the slice manifest, and derive the related code objects for documentation.
Why use it?
It prevents the process scope from being guessed or listed manually and requires a real person who can answer functional questions before work begins.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/gixsy95/abap_wiki/slice-init
Any agent
npx skills add Gixsy95/abap_wiki --skill slice-init
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.

agentmods badge for slice-init

README.md
[![agentmods](https://agentmods.dev/badge/skills/gixsy95/abap_wiki/slice-init.svg)](https://agentmods.dev/skills/gixsy95/abap_wiki/slice-init)
Your own site
<a href="https://agentmods.dev/skills/gixsy95/abap_wiki/slice-init"><img src="https://agentmods.dev/badge/skills/gixsy95/abap_wiki/slice-init.svg" alt="Measured on agentmods" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 919 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00086 $0.00919
Opus 5 $0.00043 $0.00460
Sonnet 5 $0.00017 $0.00184
Haiku 4.5 $0.00009 $0.00092

Measured 5d ago against content hash 3add4bb8e792, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

slice-init 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 5d 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/slice-init/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Slice-init - creating an L2 slice

The slice is the L2 unit of work (core/docs/03-l2-process.md §2): a business process, not an isolated page. The manifest contains ONLY the manually curated seed (anchors = entry-point, real owner = the person who will answer the questionnaires); the membership is NOT listed manually: it is derived by the pipeline by navigating the dependency graph.

Owner mandatory (§6): without a real owner the L2 phase does not start. <...>/TBD are rejected by slice-init. The owner is the person who can answer the functional questions.

Procedure

  1. Choose anchors and owner. Anchors are the curated entry-points of the process (transactions, batch jobs/programs, landmark tables). Find candidates from the package:

    .venv/Scripts/python core/src/tools/pipeline.py progress --package <DEVCLASS>
    

    The "mains" (non-includes) of a package are programs that are NOT the target of an include arc; for a cockpit, the natural anchor is the launcher + the programs it launches.

  2. Write the manifest in slices/<slice-id>/manifest.yaml starting from slices/_template/manifest.yaml. Example:

    slice:
      id: example-slice
      title: "Example custom process"
      type: domain
      owner: [email protected]      # REAL, never TBD
      experts:
        business: [email protected]
        developer: [email protected]
        basis: [email protected]
      status: draft
      anchors:
       - { ref: program-ZPROGRAM_MAIN,  role: entry-point, note: "launcher/cockpit" }
       - { ref: program-ZPROGRAM_BATCH, role: batch-job,   note: "batch processing" }
        # ... one anchor per process entry-point
      utilities: []          # opt.: ref of cross-cutting modules to exclude from rich_target
      external_inputs: []
    

    ref = the slug [[<sap_type>-<NAME>]] (the page file name without .md).

  3. Register + derive the membership:

    .venv/Scripts/python core/src/tools/pipeline.py slice-init --slice <slice-id>
    

    Creates the slices row, runs BFS from the anchors (hop<=2 on the graph), writes slices/<id>/membership.md (view) and slices/<id>/gaps.yaml (empty). The rich_target (custom main programs within 1 hop, non-utility, already L1; excludes includes _TOP/_SCR/_F01) is the working surface: the objects that will receive functional documentation. Functional analysis targets the main, not its includes.

Read the full file on GitHub · 75 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.

  1. 5d ago First seen · 75 lines · 86 tokens per session scan A 3add4bb8e792

Subscribe to this mod's changes

slice-init is a skill published in the GitHub repository Gixsy95/abap_wiki (44 stars, last pushed 4d ago), licensed MIT. It adds 86 tokens to every session and 919 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.

Related

Other skills, from other repositories