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-ingestnpx skills add choiyounggi/dev-loop --skill wiki-ingestgit 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 | $0.00058 | $0.00799 |
| Opus 5 | $0.00029 | $0.00400 |
| Sonnet 5 | $0.00012 | $0.00160 |
| Haiku 4.5 | $0.00006 | $0.00080 |
Grade A, and why
wiki-ingest scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ingest
In the dev-loop plugin. The wiki lives at the plugin root. When you run this skill by hand for reference, read paths (
INDEX.md,wiki/,templates/,AGENTS.md) against${CLAUDE_PLUGIN_ROOT}/. When this skill is driven byknowledge-flushto open a PR, that skill first prepares a writable git checkout of the dev-loop repo and passes you its path as<wiki_root>— do all reading and writing there (never edit the installed plugin dir, which is read-only and untracked).knowledge-flushhandles the branch/commit/PR after you finish; your job is only the routed, sourced edit + plumbing update.
Input: one unit of knowledge. Either a source (doc, article, post-mortem, benchmark) or a distilled lesson ("we hit X; doing Y fixed it because Z").
Steps
-
Extract the case. State the knowledge as: trigger situation → directive → why → evidence. If you cannot fill "trigger situation" precisely, stop: ask the contributor what situation makes this advice apply. Knowledge without a trigger cannot be routed and pollutes context.
-
Convert prohibitions. If the input arrives as "never do X" / "avoid X", rewrite it as the replacement action: "when , do Y". Keep the prohibition only as an
Instead ofrow paired with Y. -
Route. Match the case to a domain via
INDEX.md, then to a category via the domainindex.md. If no category fits, create one (update the domain index) — but first re-check that an existing category doesn't already cover it under a different name. -
Merge before creating. Read every existing page in the target category whose "load when" line overlaps the new case.
- Same trigger, same directive → add the new source / edge case to that page.
- Same trigger, conflicting directive → do NOT overwrite. Add the conflict to the
page under
Edge casesif it is condition-dependent, or flag it inlog.mdascontradictionfor the owner to resolve. - New trigger → create a new page from
templates/page.md.
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 · 60 lines · 58 tokens per session scan A dfeac544c8e9
wiki-ingest is a skill published in the GitHub repository choiyounggi/dev-loop (4 stars, last pushed 3d ago), licensed MIT. It adds 58 tokens to every session and 799 once invoked, about $0.0003 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.