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-plannpx skills add choiyounggi/dev-loop --skill wiki-plangit 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 | $0.00062 | $0.01839 |
| Opus 5 | $0.00031 | $0.00920 |
| Sonnet 5 | $0.00012 | $0.00368 |
| Haiku 4.5 | $0.00006 | $0.00184 |
Grade A, and why
wiki-plan scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan — decompose work into small-model-executable tasks
In the dev-loop plugin. The wiki is bundled with the plugin, not in the user's project. Resolve every
INDEX.md,wiki/<...>.md,AGENTS.md, andtemplates/path in this skill against${CLAUDE_PLUGIN_ROOT}/(the installed plugin root), NOT the current working directory. Read the wiki from there; write plan output (plans/<feature>/) into the user's project as described in step 5.How this plugs into the loop.
loop-implementcalls this skill as its step 2 (Plan) — mandatory. Produce the wiki-grounded## Decisionstable, the ordered## Task order, and onetasks/NN-*.mdper task naming the exact wiki pages it needs.loop-implementis the single implementer — it then executes those tasks in order, loading each task's named pages and running the verification loop (Red → Green → run → audit) per task. (orchestrateuses the same output to fan tasks across sessions, each session runningloop-implement.) Every decision must cite awiki/page or be marked[no-wiki].
You are the planner. The implementer will be a small model with no memory of this planning session. Its entire world per task = one task file + the wiki pages that file names + the artifacts earlier tasks produced. Every decision you leave unmade becomes the small model's guess — and guesses are where errors enter.
Rule zero
Decisions live in the plan; execution lives in the tasks. If writing a task makes you type "choose", "decide", "as appropriate", or "either" — stop, make that decision now, and write the decision into the task.
Steps
-
Clarify the goal. State what is being built, the acceptance criteria, and the stack (language, framework, DB). If the requester left a load-bearing choice open (stack, auth mechanism, data model), resolve it with them or state your chosen default explicitly in
plan.md— the small model must never pick. -
Wiki routing sweep. Read the wiki's
INDEX.md, then theindex.mdof every domain the work touches. For each design decision in this work, find the page that owns it (match "load when" lines). Build the decision→page map, e.g. for a login feature:- users table shape →
wiki/databases/schema-design/requirements-to-tables.md,naming-conventions.md,column-data-types.md - PK type →
wiki/databases/schema-design/primary-key-choice.md - re-signup after delete →
soft-delete.md+partial-and-expression-indexes.md - auth mechanism choice →
wiki/security/authn/session-vs-token.md - server token handling →
wiki/backend/auth/jwt-server-side.md - client token handling →
wiki/frontend/auth/token-handling-client-side.mdApply those pages' directives NOW to make the decisions; record decision + page id inplan.md. A decision no wiki page covers → decide from your own judgment, mark it[no-wiki], and note it as an ingest candidate.
- users table shape →
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 · 141 lines · 62 tokens per session scan A 5cd7049f9b77
wiki-plan is a skill published in the GitHub repository choiyounggi/dev-loop (4 stars, last pushed 2d ago), licensed MIT. It adds 62 tokens to every session and 1,839 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.