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 skills add dentiny/kon --skill pre-plan-gategit clone --depth 1 https://github.com/dentiny/konWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/dentiny/kon/pre-plan-gate)<a href="https://agentmods.dev/skills/dentiny/kon/pre-plan-gate"><img src="https://agentmods.dev/badge/skills/dentiny/kon/pre-plan-gate/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/dentiny/kon/pre-plan-gate"><img src="https://agentmods.dev/badge/skills/dentiny/kon/pre-plan-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00056 | $0.01606 |
| Opus 5.5 | $0.00022 | $0.00642 |
| Sonnet 5.5 | $0.00011 | $0.00321 |
| Haiku 4.5 | $0.00006 | $0.00161 |
Grade A, and why
pre-plan-gate 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 1mo 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pre-Plan Gate
Owner: orchestrator
Consumers: /kon:team, /kon:design, /kon:debug, and /kon:begin routes that enter those pipelines
Core principles: follow skills/core-principles and skills/ask-dont-guess. Planning without sufficient understanding hides the issue — do not let Mugi write steps that rest on guessed scope, behavior, or constraints.
When this gate runs
| Command | After | Before |
|---|---|---|
/kon:team |
🎸 Azusa (+ optional 📚 Jun) | 🍰 Mugi plan |
/kon:design |
🎸 Azusa (+ optional Jun) | 🍰 Mugi plan v1 |
/kon:debug |
🎸 Azusa + orchestrator writes debug.md |
🍰 Mugi fix proposals |
Skip only when:
- Plan reuse on
/kon:team— user chose to reuse an existing plan that already passed this gate (e.g. after/kon:design), and no re-plan. - Re-plan after user explicitly chose re-run Azusa + Mugi — gate runs again.
Never skip in --yolo mode. YOLO skips checkpoints inside an approved plan; it does not skip understanding before planning.
Orchestrator workflow
- Read inputs (paths only — do not paste bodies into chat):
sessions/<SID>/explore.md(team/design).kon/research.mdif present- User's original task / bug description
- For debug:
sessions/<SID>/debug.mdafter Azusa
- Summarize Azusa's unknown unknowns — one line each from
## Unknown unknowns(omit if section absent). - Ask the user questions — see Question mix below. Use prose or a short numbered list; use AskUserQuestion only when options are converged.
- Wait for answers. Run:
python3 $KON_ROOT/scripts/kon_session.py wait-for-user --id "$SID" \ --after decision --summary "Pre-plan understanding — answer questions before Mugi?" - Evaluate answers. If material gaps remain → ask follow-ups (same gate; do not spawn Mugi). If user says "I don't know" on something that changes the plan → record as open in
understanding.mdand either ask again with narrower options or stop with "cannot plan until X is known." - Write artifact —
sessions/<SID>/understanding.md(template below). - Spawn Mugi with pointer only:
UNDERSTANDING_FILE: sessions/<SID>/understanding.md EXPLORE_FILE: sessions/<SID>/explore.md PLAN_FILE: … Read UNDERSTANDING_FILE before planning. Do not replan without addressing every answered question. - After user answers and before Mugi:
user-continued --summary "Pre-plan understanding complete".
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.
- 1mo ago First seen · 150 lines · 56 tokens per session scan A 61c1e9919691
pre-plan-gate is a skill published in the GitHub repository dentiny/kon (3 stars, last pushed 3mo ago), licensed MIT. It adds 56 tokens to every session and 1,606 once invoked, about $0.0002 per session on Opus 5.5. 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
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…