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 skills add eduardoabreu81/livewiki --skill bootstrap-wikigit 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/skills/eduardoabreu81/livewiki/bootstrap-wiki)<a href="https://agentmods.dev/skills/eduardoabreu81/livewiki/bootstrap-wiki"><img src="https://agentmods.dev/badge/skills/eduardoabreu81/livewiki/bootstrap-wiki.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 5.1 | $0.00039 | $0.00794 |
| Opus 5 | $0.00019 | $0.00397 |
| Sonnet 5 | $0.00008 | $0.00159 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
bootstrap-wiki 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 7d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bootstrap-wiki
Build the repository's initial wiki through livewiki's persistent MCP task
queue. Use this skill when livewiki status reports no documented pages or
when the user explicitly asks for the initial wiki.
Do not use this skill for documentation debt created by a completed code
change. Once a wiki exists, use the document-as-you-go skill for that short,
reactive maintenance loop.
Work in bounded batches
A large repository can produce dozens or hundreds of tasks. Choose a bounded batch that fits comfortably in the remaining context, complete only that batch, and report progress to the user before continuing.
Stopping midway is safe. The queue and its checkpoints are persistent. The
next call to livewiki_next_task resumes the same run, and an in-flight task is
offered again after a disconnect. Never trade accuracy for draining the whole
queue in one context window.
Bootstrap loop
Repeat these steps for the current bounded batch:
- Call
livewiki_next_task. - If it returns a task, note its
taskId,kind,targetPath, completeclosedKeys,sourcePaths, format contract, validation data, and attempt budget. - Read the returned source paths with your own file-reading tools. The task provides paths rather than source bytes; inspect the repository before writing.
- Write the complete Markdown page required by the format contract. Treat the task's closed list as the only allowed source of canonical keys.
- Call
livewiki_write_docwith the exactpath, completecontent, and returnedtaskId. - If the write is rejected, use the returned anchor, section, or contract
diagnostics to correct it. Attempts are bounded by the server. If a task is
exhausted and becomes
failed, report it and continue withlivewiki_next_task; do not loop on it. - Continue until the current batch is complete or the remaining context says to stop.
After each batch, tell the user the run ID, how many tasks completed or failed, the current task if one remains in flight, and that another invocation can resume safely.
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.
- 7d ago First seen · 83 lines · 39 tokens per session scan A 07958ec8dab0
bootstrap-wiki is a skill published in the GitHub repository eduardoabreu81/livewiki (0 stars, last pushed 2d ago), licensed MIT. It adds 39 tokens to every session and 794 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
docpull-research
Use the docpull MCP tools (listindexed, ensuredocs, grepdocs, readdoc, fetchurl) to ground answers in real web/source material when the user asks about a specific library, framework, API, vendor, product page, website, or public source URL. Activate on questions like "how do I X in [library]", "what's the API for…
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.
setup
First-time setup wizard for Gnosis MCP. Install, init the database, ingest a docs folder, wire your editor — in that order.
status
Verify gnosis-mcp server connectivity, schema integrity, and corpus health. Use when MCP calls fail, return empty, or return unexpected data.
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.
eval
Measure retrieval quality on your corpus — Hit@5, MRR, nDCG@10, Precision@5. Thin wrapper around gnosis-mcp eval with regression tracking against a saved baseline, plain-English interpretation, and tuning pointers when numbers look off. Use after every ingest or config change.