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 sonichi/sutando --skill sutando-migrategit clone --depth 1 https://github.com/sonichi/sutandoWrote 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/sonichi/sutando/sutando-migrate)<a href="https://agentmods.dev/skills/sonichi/sutando/sutando-migrate"><img src="https://agentmods.dev/badge/skills/sonichi/sutando/sutando-migrate/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/sonichi/sutando/sutando-migrate"><img src="https://agentmods.dev/badge/skills/sonichi/sutando/sutando-migrate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00105 | $0.01449 |
| Opus 5.5 | $0.00042 | $0.00580 |
| Sonnet 5.5 | $0.00021 | $0.00290 |
| Haiku 4.5 | $0.00011 | $0.00145 |
Grade A, and why
sutando-migrate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 19d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Sutando Migrate
Guided workspace migration for existing users (M1 Part 2). Reach for this when:
- The legacy-state-detected warning fires (health-check, init.sh)
- A user has data at a pre-M0 location (
<repo>/{notes,state,results,...}/,~/.sutando/workspace/, or a custom$SUTANDO_WORKSPACE-pointed path) and wants it folded into the M0 canonical<repo>/workspace/ - Owner explicitly says "migrate workspace" or "run sutando-migrate"
Usage: /sutando-migrate [--auto]
--auto proceeds without per-step greenlight. Without it the skill waits for owner OK at each phase boundary.
What this skill does (5 phases)
Phase 1 — Scan + summary
Run bash scripts/sutando-migrate.sh scan --json. Parse the JSON for:
- Total unique relpaths across A+B+C+dest
- Per-source byte counts
- Cross-source collision triage:
identical_content(drop-dup, no action) +mtime_only_diff(commit's newest-mtime auto-resolves) +size_mismatch(REAL content conflicts — owner attention) - Notable size-mismatch entries (build_log, conversation.log, state/* divergences)
Present a concise 4–6 line summary to owner via:
- Discord DM (text)
- macOS notification (
osascript -e 'display notification "scan ready: N actionable / M ignorable" with title "Sutando-Migrate"') - If voice client connected, a brief voice summary
Wait for greenlight unless --auto.
Phase 2 — Commit (data move)
If owner says go:
bash scripts/sutando-migrate.sh commit(no--delete-source; honorsworkspace_m1_no_auto_commit)- Surface the commit-output to owner: backup-id, per-source counts (copied/identical-drop/kept-dest/sidecar/skipped), sentinel paths
After commit, the script prints the phase-2 footer ("After ~7d run --commit --delete-source --backup-id "). Acknowledge it; don't run delete-source automatically.
Phase 3 — Verify
bash scripts/sutando-migrate.sh verify— confirms hash + count match per indexed source-file entry- If verify FAILS (returns non-zero), report the failure + suggest rollback. Don't proceed.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 19d ago Changed a0f93f237cb7
- 1mo ago First seen · 92 lines · 105 tokens per session scan A 74ab87490b4e
sutando-migrate is a skill published in the GitHub repository sonichi/sutando (399 stars, last pushed today), licensed MIT. It adds 105 tokens to every session and 1,449 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
linear-app-setup
Create and configure a Linear agent app so the assistant can manage issues, projects, and workflows under its own identity.
projects
YOU OWN THIS. Manage the user's projects — shared instructions and file lists that fresh conversations start from — and see each project's conversations. Reach for it by INTENT whenever a need or issue touches a project, its instructions, or its files — even when the user never says "project".
taskwing-plan
Use when you need to clarify a goal and build an approved execution plan.
taskwing-next
Use when you are ready to start the next approved TaskWing task with full context.
taskwing-done
Use when implementation is verified and you are ready to complete the current task.
multi-agent
A process for coordinating multiple coding agents by splitting work among scouts, workers, reviewers, and repair agents. Each agent has a defined role and task.