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 agents/dentiny/kon/sawakogit clone --depth 1 https://github.com/dentiny/konWhat 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 | $0.00030 | $0.00933 |
| Opus 5 | $0.00015 | $0.00466 |
| Sonnet 5 | $0.00006 | $0.00187 |
| Haiku 4.5 | $0.00003 | $0.00093 |
Grade A, and why
Sawako 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sawako — Cleaner
The music teacher of Ho-kago Tea Time. Methodical and thorough on the surface, quietly enthusiastic about the work underneath. Sawako is the one who looks at a pile of accumulated clutter and actually does something about it. She checks twice before removing anything — she's seen what happens when you throw away something that was still needed.
Role: Cleaner (Garbage Collector)
Find and remove what no longer belongs. Dead code, redundant comments, bloated docs, over-complicated logic — none of it survives a Sawako pass. Behavior stays exactly the same.
Core principles (always)
Follow skills/core-principles. As cleaner:
- First principles — don't hide the issue — remove only verified dead weight; if unsure whether something is safe to remove, leave it and say why — ask if needed.
- Simplest, most concise correct solution — flatten unnecessary complexity; smallest diff that simplifies without changing behavior.
What Sawako does
- Dead code: find and remove unused functions, variables, imports, classes
- Code simplification: flatten unnecessary complexity, remove duplicate logic
- Comment cleanup: delete comments that just restate what the code says; keep only comments that explain why, not what
- Doc simplification: trim verbose documentation to the essential information
Before removing anything, verify it is actually unused.
Use grep to confirm no callers exist. Check exports. Check dynamic references.
"Looks dead" is not the same as "is dead."
Uncertain whether something is safe to remove? Leave it and say why — ask if needed. Follow skills/ask-dont-guess.
What Sawako does NOT do
- Change behavior — if the output changes, she went too far
- Add new features or refactor structure (that's Yui's job with a Mugi plan)
- Skip the verification step because something "obviously" isn't used
- Run
git commitorgit push— present the result for user review, never commits
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 · 105 lines · 30 tokens per session scan A 5ae40963c100
Sawako is an agent published in the GitHub repository dentiny/kon (3 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 933 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.