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 design-debategit 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/design-debate)<a href="https://agentmods.dev/skills/dentiny/kon/design-debate"><img src="https://agentmods.dev/badge/skills/dentiny/kon/design-debate/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/design-debate"><img src="https://agentmods.dev/badge/skills/dentiny/kon/design-debate.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 | $0.00035 | $0.01907 |
| Opus 5.5 | $0.00014 | $0.00763 |
| Sonnet 5.5 | $0.00007 | $0.00381 |
| Haiku 4.5 | $0.00003 | $0.00191 |
Grade A, and why
design-debate 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Design Debate
Consumer: /kon:design.
Core principles (always)
Follow skills/core-principles. Design debate exists to stress-test plans before code is written. Both challenger and reviser optimize for:
- First principles — don't hide the issue — restate the actual problem; does the plan solve that problem, or inherit assumptions / over-engineer?
- Simplest, most concise correct solution — most direct design Yui can execute without unnecessary layers.
Azusa must challenge complexity that lacks first-principles justification. Mugi must revise toward simpler designs when challenges are valid.
Do not invent risks or requirements to fill a debate round — if the plan is sound but you lack evidence, say so and ask. Follow skills/ask-dont-guess.
Design debate is real multi-agent argument, not the orchestrator summarizing both sides. Each round is a separate Task spawn with the agent file + this skill in context.
Roles
| Phase | Agent | Mode | Writes |
|---|---|---|---|
| Explore | 🎸 Azusa | default | nothing (report only) |
| Plan v1 | 🍰 Mugi | default | .kon/plan-<session-id>.md |
| Challenge | 🎸 Azusa | challenge | .kon/design-debate-<session-id>.md (challenges section) |
| Revise | 🍰 Mugi | revise | .kon/plan-<session-id>.md + .kon/design-debate-<session-id>.md (responses) |
| Confirm | user | — | — |
Artifacts
.kon/design-debate-<session-id>.md
Created on first challenge round. Threaded log of argument:
# Design debate: <task name>
## Round 1 — Azusa challenges
### C1: <short title>
<why this is a gap, risk, or wrong assumption — cite files/lines>
### C2: ...
## Round 1 — Mugi responses
| ID | Verdict | Response | Plan change |
|----|---------|----------|-------------|
| C1 | accepted | ... | Step 2 split into 2a/2b |
| C2 | rejected | Plan already covers via Step 4 acceptance | none |
## Round 2 — Azusa challenges (only with --deep)
...
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 · 188 lines · 35 tokens per session scan A 96c61d5bc91f
design-debate is a skill published in the GitHub repository dentiny/kon (3 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 1,907 once invoked, about $0.0001 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
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…