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/teamniteo/hakuto/scaffold-syncnpx skills add teamniteo/hakuto --skill scaffold-syncgit clone --depth 1 https://github.com/teamniteo/hakutoWrote 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/teamniteo/hakuto/scaffold-sync)<a href="https://agentmods.dev/skills/teamniteo/hakuto/scaffold-sync"><img src="https://agentmods.dev/badge/skills/teamniteo/hakuto/scaffold-sync.svg" alt="Measured on agentmods" 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 | $0.00160 | $0.04449 |
| Opus 5 | $0.00080 | $0.02225 |
| Sonnet 5 | $0.00032 | $0.00890 |
| Haiku 4.5 | $0.00016 | $0.00445 |
Grade C, and why
scaffold-sync scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- **No `rm -rf`** — deletions are one file at a time, only with explicit per-file approval. How it starts
The opening of the file, as written. The whole thing — 413 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scaffold Sync Skill
Pull selective scaffold updates from the installed Hakuto plugin into an existing site. The skill is interactive and report-first — every change is shown to the user and applied only on explicit per-file approval. State is persisted in .hakuto-sync.json at the site root so each run only considers drift since the last sync.
Run when the user says any of:
- "Sync scaffold"
- "Check for scaffold updates"
- "Pull scaffold changes"
- "Update scaffold"
- "What's new in the scaffold"
- "Is my scaffold current?"
Execution Flow
1. Locate upstream
Resolve the plugin scaffold:
PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:?run scaffold-sync from a Hakuto plugin context (CLAUDE_PLUGIN_ROOT not set)}"
SCAFFOLD="${PLUGIN_ROOT}/scaffold"
test -d "$SCAFFOLD" || { echo "ERROR: $SCAFFOLD missing — plugin install is incomplete." >&2; exit 1; }
If CLAUDE_PLUGIN_ROOT is unset or scaffold/ is missing, stop with a one-line error. Do not attempt fallbacks.
2. Resolve current upstream identity
Try git first, fall back to a content hash:
if git -C "$PLUGIN_ROOT" rev-parse --git-dir >/dev/null 2>&1; then
CURRENT_SHA=$(git -C "$PLUGIN_ROOT" rev-parse HEAD)
CURRENT_METHOD="git"
else
# Stable content hash of the scaffold tree (excludes generated/state dirs)
CURRENT_SHA=$(find "$SCAFFOLD" -type f \
-not -path '*/node_modules/*' \
-not -path '*/.astro/*' \
-not -path '*/dist/*' \
-not -path '*/.wrangler/*' \
-not -path '*/.git/*' \
| sort | xargs sha256sum | sha256sum | awk '{print $1}')
CURRENT_METHOD="content-hash"
fi
Record both CURRENT_SHA and CURRENT_METHOD for the state file.
Also read the current plugin version from ${PLUGIN_ROOT}/.claude-plugin/plugin.json:
CURRENT_PLUGIN_VERSION=$(jq -r '.version // "unknown"' "${PLUGIN_ROOT}/.claude-plugin/plugin.json" 2>/dev/null || echo "unknown")
Record CURRENT_PLUGIN_VERSION for the state file and migration report.
3. Read site state
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.
- 4d ago First seen · 413 lines · 160 tokens per session scan C f928ffaae5b9
scaffold-sync is a skill published in the GitHub repository teamniteo/hakuto (5 stars, last pushed 10d ago), licensed MIT. It adds 160 tokens to every session and 4,449 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…