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/narailabs/doc-wiki/querygit clone --depth 1 https://github.com/narailabs/doc-wikiWhat 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 | $0.00018 | $0.00542 |
| Opus 5 | $0.00009 | $0.00271 |
| Sonnet 5 | $0.00004 | $0.00108 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
query 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.
What it actually says
Invoke the doc-wiki skill to run the /doc-wiki:query workflow with the user's arguments: $ARGUMENTS
Call Skill(doc-wiki, "query $ARGUMENTS"). The skill orchestrator reads skills/doc-wiki/SKILL.md, locates the ### /doc-wiki:query — Summary-first search + synthesis section, and dispatches one of four modes:
- Synthesis mode (default): runs the summary-first flow — read
summaries.md, score relevance, load top-N pages, follow links up to 5 levels, synthesize with citations, surface contradictions, archive tooutputs/queries/, log token efficiency. After the answer, prompts "Save this answer as a permanent wiki page?" (gated by autonomy mode). - Path mode (when
--fromand--toare present): shells out tograph_ops.js pathagainst<wiki-root>/graph/edges.jsonland returns the typed-edge chain connecting the two concepts. Skips summary-first scoring, link-following, synthesis, and the promote prompt. - Promote mode (when
--promote <file|last|N>is present): converts an archived answer inoutputs/queries/into a wiki page (frontmatter, citation→link rewriting, topic placement). Argument forms:last/latest→ most recent; integerN→ Nth most recent; path → as-is; single token → filename substring match; empty → list-and-pick. - Review mode (when
--reviewis present): bulk archive triage with per-item P/S/D/A approval, honoring autonomy mode. Supports--since <duration>,--limit <N>, and--topic <dir>for filtering.
If $ARGUMENTS is empty, ask the user what they want: a question to answer (synthesis mode), two concepts to connect (path mode), an archive to promote, or a batch review of archives.
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 · 17 lines · 18 tokens per session scan A 1a4b001e1851
query is a command published in the GitHub repository narailabs/doc-wiki (13 stars, last pushed 2d ago), licensed Apache-2.0. It adds 18 tokens to every session and 542 once invoked, about $0.0001 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.