wiki-query

A development wiki lookup tool that answers questions using only relevant pages from a project's internal documentation, with citations. It can also record missing answers and add useful recurring knowledge back to the wiki.

In plain words
What is it for?
Use it to answer development questions, route through wiki indexes, cite the pages used, report gaps, and save synthesized guidance when it is likely to be needed again.
Why use it?
It avoids scanning unrelated documentation and makes clear which answers come from the wiki and which do not. This helps developers trace advice back to its source.

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/choiyounggi/dev-loop/wiki-query
Any agent
npx skills add choiyounggi/dev-loop --skill wiki-query
Clone the repo
git clone --depth 1 https://github.com/choiyounggi/dev-loop

Made for: Claude Code, Codex.

Per session 49 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 385 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 $0.00049 $0.00385
Opus 5 $0.00024 $0.00192
Sonnet 5 $0.00010 $0.00077
Haiku 4.5 $0.00005 $0.00038

Measured 2d ago against content hash 91e699159c1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wiki-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.

skills/wiki-query/SKILL.md · 35 lines

What it actually says

Query

In the dev-loop plugin. Resolve INDEX.md and wiki/<...>.md paths against ${CLAUDE_PLUGIN_ROOT}/ (the installed plugin root), not the working dir.

Input: a question or an active task that needs guidance.

Steps

  1. Route, don't scan. Follow the routing protocol in AGENTS.md: INDEX.md → domain index.md → load only pages whose "When this applies" matches. Never bulk-load a domain.

  2. Answer from pages, cite pages. Compose the answer from the loaded pages' directives and edge-case tables. Cite each page id you used. Where a page cites external sources, surface them.

  3. Say what the wiki doesn't know. If no page matches, say so explicitly and answer from general knowledge clearly labeled as not wiki-backed. Do not blend wiki-backed and unbacked claims without labels.

  4. Compound. If the answer required synthesizing 2+ pages or filled a gap, and the question is one that will recur, run skills/wiki-ingest/SKILL.md on the synthesis (the answer's evidence chain is its source list). One-off trivia does not get a page.

  5. Log gaps. If the wiki had no answer, append ## [YYYY-MM-DD] gap | <question> to log.md so lint can propose research.

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. 2d ago First seen · 35 lines · 49 tokens per session scan A 91e699159c1a

Subscribe to this mod's changes

wiki-query is a skill published in the GitHub repository choiyounggi/dev-loop (4 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 385 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.

Related

Other skills, from other repositories

kb-create

Operator procedure to declare and provision a new Knowledge Base GitOps-style, so it survives pod restarts.

BeppeTemp/cartographer · 24 tokens

kb-import

Agent-guided procedure to import an existing non-OKF wiki or knowledge base (Obsidian vault, markdown folder, wiki export) into a Cartographer KB, incrementally and without big-bang LLM rewriting.

BeppeTemp/cartographer · 48 tokens

deploy

Rilascia una nuova versione di Cartographer — merge della release PR di release-please, attesa della pipeline GitHub (binari, brew, ghcr), bump del manifest homelab, verifica rollout Flux e update del client locale via brew. Usare quando l'utente chiede di deployare/rilasciare una nuova versione di server e/o client.

BeppeTemp/cartographer · 78 tokens

implement-plan

Orchestrates implementation of one or more approved plan issues (label plan) into merged PRs through wave planning, delegation to dev subagents in isolated worktrees, coordinator review, and ordered squash-merge with topic-owned documentation conflict resolution. Use when the user asks to implement, ship, or land open…

BeppeTemp/cartographer · 107 tokens

academic-paper-drafting

End-to-end academic paper drafting for CHI, HBR, journals, and conferences with venue-specific templates, drafting workflows, and revision strategies.

fabioc-aloha/Alex_Skill_Mall · 34 tokens

research-first-development

Build knowledge bases that build software — research before code, teach before execute.

fabioc-aloha/Alex_Skill_Mall · 18 tokens