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/verifygit clone --depth 1 https://github.com/eduardoabreu81/livewikiWrote 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/commands/eduardoabreu81/livewiki/verify)<a href="https://agentmods.dev/commands/eduardoabreu81/livewiki/verify"><img src="https://agentmods.dev/badge/commands/eduardoabreu81/livewiki/verify.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 | $0.00000 | $0.01391 |
| Opus 5 | $0.00000 | $0.00696 |
| Sonnet 5 | $0.00000 | $0.00278 |
| Haiku 4.5 | $0.00000 | $0.00139 |
Grade A, and why
verify 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 4d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
livewiki verify command
This page documents the livewiki verify CLI subcommand, which checks a generated wiki for the kinds of corruption that would break readers or CI pipelines.
When to use this page
- Wire
livewiki verifyinto a CI pipeline so build steps fail when the wiki no longer matches its index. - Inspect what counts as a "verification failure": broken anchors, altered manual blocks, and broken internal links.
- Choose between the default human-readable report and a machine-readable JSON report using the
--jsonflag. - Debug non-zero exits from the verifier by understanding the option parsing, error handling, and exit-code flow inside
registerVerify.
How it fits
The file lives at packages/cli/src/commands/verify.ts, inside the @livewiki/cli package's commands directory. It sits in the command-registration layer of the CLI: each file here exports one registerXxx(program) function that a higher-level CLI bootstrap attaches to a commander Command instance. registerVerify delegates all heavy lifting to the @livewiki/core/verify module — specifically runVerify (the actual checker) and formatVerifyHuman (the text reporter) — and adds only the CLI-shaped concerns: parsing VerifyOptions, resolving the repository root, switching between JSON and human output, and translating outcomes into a process exit code. The verifier itself is what walks the wiki pages and the index; this file is the thin adapter that exposes it as a subcommand.
Diagram
%% livewiki/diagrams/commands-verify.mmd
Command registration
The single responsibility of this file is to teach the top-level commander program how to invoke the verify subcommand and how to render the result.
export function registerVerify(program: Command): void
registerVerify takes the parent commander Command instance and returns nothing; attaching a subcommand to it mutates the program in place.
// packages/cli/src/commands/verify.ts
export function registerVerify(program: Command): void {
program
.command("verify")
.description(
"validate wiki: anchors + manual blocks + internal links. Exit ≠ 0 on failure (Phase 2, CI-friendly)",
)
.action(async (_options: VerifyOptions, command: Command) => {
const opts = command.optsWithGlobals<VerifyOptions>();
const json = Boolean(opts.json);
const repoRoot = path.resolve(process.cwd(), opts.repo ?? ".");
let result: VerifyResult;
try {
result = await runVerify(repoRoot);
} catch (err) {
process.stderr.write(`livewiki verify: error — ${(err as Error).message}\n`);
// An abrupt exit after writing stderr can crash libuv on Windows
// while I/O is pending. Let Node drain the event loop naturally.
process.exitCode = 1;
return;
}
if (json) {
process.stdout.write(JSON.stringify(result) + "\n");
} else {
process.stdout.write(formatVerifyHuman(result) + "\n");
}
// CI-friendly: exit code != 0 if there are errors
if (!result.ok) process.exitCode = 1;
});
}
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.
- 4d ago First seen · 87 lines · 0 tokens per session scan A a1f59c9563bc
verify is a command published in the GitHub repository eduardoabreu81/livewiki (0 stars, last pushed 8d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,391 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
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…
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-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.
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…
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…
query
Queries the abapwiki knowledge base to answer questions about custom ABAP code (what an object does, which tables it uses, who calls it, dependencies, bugs). Navigates index -> package -> pages; can extend the answer with the SAP system via MCP abap-fs in read-only mode, explicitly citing wiki vs. system.