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 skills/choiyounggi/dev-loop/wiki-querynpx skills add choiyounggi/dev-loop --skill wiki-querygit clone --depth 1 https://github.com/choiyounggi/dev-loopWhat 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 | $0.00049 | $0.00385 |
| Opus 5 | $0.00024 | $0.00192 |
| Sonnet 5 | $0.00010 | $0.00077 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
wiki-query scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Query
In the dev-loop plugin. Resolve
INDEX.mdandwiki/<...>.mdpaths against${CLAUDE_PLUGIN_ROOT}/(the installed plugin root), not the working dir.
Input: a question or an active task that needs guidance.
Steps
-
Route, don't scan. Follow the routing protocol in
AGENTS.md:INDEX.md→ domainindex.md→ load only pages whose "When this applies" matches. Never bulk-load a domain. -
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.
-
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.
-
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.mdon the synthesis (the answer's evidence chain is its source list). One-off trivia does not get a page. -
Log gaps. If the wiki had no answer, append
## [YYYY-MM-DD] gap | <question>tolog.mdso lint can propose research.
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 · 35 lines · 49 tokens per session scan A 91e699159c1a
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.
Other skills, from other repositories
kb-create
Operator procedure to declare and provision a new Knowledge Base GitOps-style, so it survives pod restarts.
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.
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.
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…
academic-paper-drafting
End-to-end academic paper drafting for CHI, HBR, journals, and conferences with venue-specific templates, drafting workflows, and revision strategies.
research-first-development
Build knowledge bases that build software — research before code, teach before execute.