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 wasintoh/toh-framework --skill version-controlgit clone --depth 1 https://github.com/wasintoh/toh-frameworkWrote 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/wasintoh/toh-framework/version-control)<a href="https://agentmods.dev/skills/wasintoh/toh-framework/version-control"><img src="https://agentmods.dev/badge/skills/wasintoh/toh-framework/version-control/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/wasintoh/toh-framework/version-control"><img src="https://agentmods.dev/badge/skills/wasintoh/toh-framework/version-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 204 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Excessive Agency · line 286 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00080 | $0.01689 |
| Opus 5.5 | $0.00032 | $0.00676 |
| Sonnet 5.5 | $0.00016 | $0.00338 |
| Haiku 4.5 | $0.00008 | $0.00169 |
Grade A, and why
version-control 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 — 292 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⏪ Version Control Skill
Purpose: Easy undo/rollback without knowing git Version: 1.0.0 Author: Toh Framework Team
Overview
This skill enables users to undo changes easily using natural language, without needing to understand git commands or version control concepts.
Core Principle
User says: "ย้อนกลับ" or "undo"
AI does: git stash/revert + cleanup + restart dev
User sees: "เรียบร้อยครับ กลับไปก่อนแก้ไขล่าสุดแล้ว"
HIDE GIT COMPLEXITY - User just says what they want.
Trigger Words
Undo/Rollback
| User Says | AI Understands |
|---|---|
| ย้อนกลับ | Undo last change |
| undo | Undo last change |
| เอาอันเดิมคืน | Revert to previous |
| ไม่เอาแล้ว | Discard current changes |
| กลับไปก่อนหน้า | Go back to previous state |
| ยกเลิกที่ทำไป | Cancel what was done |
| rollback | Revert changes |
Checkpoint/Save
| User Says | AI Understands |
|---|---|
| save ไว้ก่อน | Create checkpoint |
| checkpoint | Create savepoint |
| เซฟไว้ | Save current state |
| บันทึกจุดนี้ | Mark this point |
Auto-Checkpoint System
AI automatically creates checkpoints at key moments:
Auto-Checkpoint Triggers
| Event | Checkpoint Name |
|---|---|
After /toh-vibe |
vibe-[project-name]-initial |
After /toh-ui completion |
ui-[component-name]-done |
After /toh-dev completion |
dev-[feature-name]-done |
After /toh-connect |
connect-supabase-done |
| Before major changes | pre-[action]-backup |
Checkpoint Storage
.toh/checkpoints/
├── checkpoint-log.json # List of all checkpoints
└── (git handles actual data)
checkpoint-log.json:
{
"checkpoints": [
{
"id": "cp-001",
"name": "vibe-coffee-shop-initial",
"timestamp": "2024-12-03T10:30:00Z",
"description": "หลังสร้างโปรเจคร้านกาแฟ",
"gitRef": "abc123"
},
{
"id": "cp-002",
"name": "ui-dashboard-done",
"timestamp": "2024-12-03T11:00:00Z",
"description": "หลังสร้าง Dashboard UI",
"gitRef": "def456"
}
]
}
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 · 292 lines · 80 tokens per session scan A 7a6d16894bbd
version-control is a skill published in the GitHub repository wasintoh/toh-framework (98 stars, last pushed 1mo ago), licensed MIT. It adds 80 tokens to every session and 1,689 once invoked, about $0.0003 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
private-github-search
Full-text search across all of the user's GitHub repos (including private ones) using a local mirror and ripgrep. Use for "where did I put X", "which repo has X", or any search spanning the user's repos - gh search code / the REST API cannot reliably search private repos.
github-attribution
Use whenever an agent authors or reads a GitHub issue, pull request, or comment body, or writes an agent-authored commit message. Covers the [[agent: ]] body trailer, Task:/Agent: commit trailer, and how to read cooperative attribution when multiple roles share one GitHub identity.
resolve-pr-feedback
Use when asked to resolve, address, fix, or reply to review feedback on a GitHub Pull Request or GitLab Merge Request, including review comments, unresolved threads, requested changes, or "apply the review comments" requests.
review-pr
Use when asked to review a GitHub Pull Request or GitLab Merge Request, including PR/MR URLs, identifiers, discussions, findings, inline comments, approvals, or request-changes actions.
implement-ticket
Use when asked to implement, build, or pick up a ticket end to end — a Jira work item, GitHub Issue, or GitLab Issue — including "implement ABC-123", "implement gh issue #137", "work on issue 137", or "pick up this ticket". Critiques the request against the code, builds it in a throwaway git worktree, verifies it with…
review-and-resolve-pr
Use when asked to review a GitHub Pull Request or GitLab Merge Request and act on the result in one autonomous pass, including "review and fix this PR", "review this MR and resolve the feedback", "close the review loop on this PR", or any request that pairs reviewing a PR/MR with applying the findings. Reviews the…