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.
npx agentmods add commands/eduardoabreu81/livewiki/batchgit clone --depth 1 https://github.com/eduardoabreu81/livewikiWhat 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 | $0.00000 | $0.02572 |
| Opus 5 | $0.00000 | $0.01286 |
| Sonnet 5 | $0.00000 | $0.00514 |
| Haiku 4.5 | $0.00000 | $0.00257 |
Grade A, and why
batch 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 2d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Batch CLI command: registration and human-readable reporting
This page documents how the livewiki batch command is registered with the Commander CLI framework and how it formats batch run reports for human consumption.
When to use this page
- Understand how the
livewiki batchcommand dispatches its subcommands (status,resume,list, and--only). - Learn how token, USD, failure, and recovery-tier information is formatted into the human-readable output for batch status and result reports.
- See how exit codes are derived from run status for non-JSON output.
- Trace how failed stage-4 tasks surface their per-attempt diagnostic history in status reports.
How it fits
This file lives in the CLI package (packages/cli/src/commands/), which is the user-facing command layer of livewiki. It depends on core batch logic imported from @livewiki/core/batch (specifically runBatch, resumeBatch, runOnly) and @livewiki/core/batch-status (buildStatusReport, listRuns). The file's role is to wire a Commander subcommand to those core functions and to translate their structured results into either JSON (via the shared emit helper) or human-readable text. It also sets the process exit code based on run status, except when JSON output is requested, in which case the exit code is always 0.
The mechanics in this file are purely about CLI orchestration and presentation: it validates user input, calls the core functions, formats the returned data, and signals the outcome through the exit code.
Diagram
%% livewiki/diagrams/commands-batch.mmd
Subcommand dispatch
The registerBatch function is the single entry point that registers the batch command on the provided Commander program. It takes a Command instance and returns void.
export function registerBatch(program: Command): void {
The function receives the Commander program and registers a batch command on it. It declares three options: --only <target> to re-run a single task, --no-refine to skip LLM refinement (Commander maps this to refine === false), and --concurrency <n> to set the stage-4 worker pool size (an integer 1..16). The action handler then resolves the repository root, parses the positional arguments, and dispatches based on the first argument.
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.
- 2d ago First seen · 153 lines · 0 tokens per session scan A 1cbbcb658df5
batch is a command published in the GitHub repository eduardoabreu81/livewiki (0 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,572 tokens. 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 2026-08-31.
Other commands, from other repositories
capture-answer
Ingests an expert's answers to an L2 questionnaire in the abapwiki knowledge base: transforms the answers (filled in the interviews/ file or given verbally) into a canonical citable expert-answer (slices/ /inputs/expert-answers/), moves gaps to 'answered' and closes the questions. Use this skill when the owner/expert…
ingest-l1
L1 analysis loop for the abapwiki knowledge base: for each batch it launches the abap-analyzer sub-agent in parallel, then the adversarial judge abap-deepcheck (separate session), applies only the analyses that pass the fail-closed gate, and commits. Resumes exactly after an interruption. Use this skill to document…
research-l2
Executes Phases 1-3 of the L2 process of the abapwiki knowledge base on a slice: launches the abap-functional-researcher sub-agent (gap discovery + multi-source auto-research: wiki -> raw/docs -> MCP abap-fs on the system read-only -> standard knowledge), ingests gaps and evidence, and generates questionnaires for…
slice-init
Creates an L2 slice in the abapwiki knowledge base: a business process on which to build functional documentation. Writes the manifest (curated anchors + mandatory real owner) and derives the membership from the dependency graph (BFS hop<=2). Use this skill to start the L2 process on a custom domain. Does not promote…
ingest-l0
L0 bootstrap of the abapwiki knowledge base: creates stubs for all custom objects from the TADIR. Use this skill to initialize the repo from scratch or to ingest a new TADIR export. Deterministic operations (no LLM sub-agent), idempotent.
lint-audit
Checks the integrity of the abapwiki knowledge base: parseable YAML frontmatter, no broken wikilinks, resolvable [VERIFIED: path:N-M] citations, non-nested confidence tags, drift between wiki and DB, synchronization between canonical agent contracts and the .claude/agents/ copies. Use this skill periodically or after…