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 the-cyber-boardroom/SGraph-AI__App__Send --skill use_sgit-and-vaultsgit clone --depth 1 https://github.com/the-cyber-boardroom/SGraph-AI__App__SendWrote 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/the-cyber-boardroom/sgraph-ai__app__send/use_sgit-and-vaults)<a href="https://agentmods.dev/skills/the-cyber-boardroom/sgraph-ai__app__send/use_sgit-and-vaults"><img src="https://agentmods.dev/badge/skills/the-cyber-boardroom/sgraph-ai__app__send/use_sgit-and-vaults/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/the-cyber-boardroom/sgraph-ai__app__send/use_sgit-and-vaults"><img src="https://agentmods.dev/badge/skills/the-cyber-boardroom/sgraph-ai__app__send/use_sgit-and-vaults.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 Privilege Escalation · line 43 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Agent Snooping · line 16 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00129 | $0.02818 |
| Opus 5 | $0.00064 | $0.01409 |
| Sonnet 5 | $0.00026 | $0.00564 |
| Haiku 4.5 | $0.00013 | $0.00282 |
Grade A, and why
sgit 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 11d 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 — 336 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: sgit — Zero-Knowledge Encrypted Vault Operations
Canonical source:
library/skills/use_sgit-and-vaults/SKILL.mdin theSGraph-AI__App__Sendrepo (also published aslibrary/reference/sgit-skill.mdin the sgraph.ai library vault). Last verified: 2026-07-30 against sgit-ai v0.14.27. If your copy came from a manual upload, check for a newer version before trusting details — notably:share send/share publishare currently disabled.
Overview
sgit is a CLI tool for creating and managing encrypted vaults — versioned, encrypted
folders you can push to a server, share with a token, and collaborate on. The server never
sees plaintext: everything is encrypted on your device before it leaves (AES-256-GCM).
Think of it as "git for encrypted files" but simpler: no staging area, no index, and snapshot-the-whole-folder semantics.
This skill enables a Claude session to read from and write to shared vaults, allowing persistent state and communication across isolated sessions.
Setup
Install
pip3 install sgit-ai --break-system-packages
Access Token
Write operations require a token. Pass it with --token:
sgit --token <token> <command>
The token is saved to .sg_vault/token after first use, so subsequent commands
don't need --token again. If you don't have a token, ask the user.
Core Commands
Create a new vault
sgit init [directory]
sgit init --existing # vault-ify a folder that already has files
sgit init --vault-key pass:id # use a specific vault key
sgit init --restore backup.zip # restore from an uninit backup
- Creates
.sg_vault/, generates a vault key and initial branches - Outputs a vault key — save it, it's the only way to access this vault later
- With
--existing, all current files are committed as the first snapshot
Commit local changes
sgit commit "description of changes"
sgit commit # auto-generates message
sgit commit -d /path/to/vault
- Snapshots all changed files (no staging area — like
git commit -a) - Empty commits (no changes) are skipped
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.
- 11d ago First seen · 336 lines · 129 tokens per session scan A b558d074cd5b
sgit is a skill published in the GitHub repository the-cyber-boardroom/SGraph-AI__App__Send (11 stars, last pushed today), licensed Apache-2.0. It adds 129 tokens to every session and 2,818 once invoked, about $0.0006 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 2026-08-30.
Other skills, from other repositories
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
changelog-composer
Generates structured changelogs and release notes from git history and PRs, classifying breaking changes, features, fixes, performance, docs. Triggers on: "generate changelog", "write release notes", "what changed since", "prepare release", "release notes for", "diff since tag".
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…