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 xg-gh-25/SwarmAI --skill s_workspace-gitgit clone --depth 1 https://github.com/xg-gh-25/SwarmAIWrote 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/xg-gh-25/swarmai/s_workspace-git)<a href="https://agentmods.dev/skills/xg-gh-25/swarmai/s_workspace-git"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_workspace-git/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/xg-gh-25/swarmai/s_workspace-git"><img src="https://agentmods.dev/badge/skills/xg-gh-25/swarmai/s_workspace-git.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 137 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.
- high Tool Misuse · line 140 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.
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 | $0.00070 | $0.01426 |
| Opus 5 | $0.00035 | $0.00713 |
| Sonnet 5 | $0.00014 | $0.00285 |
| Haiku 4.5 | $0.00007 | $0.00143 |
Grade A, and why
workspace-git 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 6d 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 — 204 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workspace Git
Git operations for SwarmWS. All commands run in the SwarmWS workspace root (~/.swarm-ai/SwarmWS/).
Quick Reference
| User says | Command |
|---|---|
| "what changed" | git status --short |
| "show me the diff" | git diff |
| "commit today's work" | Review → stage → commit with summary |
| "what did we do this week" | git log --since="1 week ago" --oneline |
| "undo last commit" | git reset --soft HEAD~1 |
| "stash my changes" | git stash push -m "description" |
| "search commits for X" | git log --all --grep="X" --oneline |
Operations
Status & Diff
# Quick status
git status --short
# Full diff (unstaged)
git diff
# Staged changes
git diff --cached
# Diff for specific file
git diff -- path/to/file
# Stat summary (files changed, insertions, deletions)
git diff --stat
# Word-level diff (useful for markdown)
git diff --word-diff
Commit Workflow
When user asks to commit:
- Review —
git status --short+git diff --stat - Summarize — Describe what changed in plain language
- Stage —
git add <specific files>(nevergit add -Ablindly) - Commit — Write a clear commit message
# Stage specific files
git add Knowledge/Notes/2026-03-15-plan.md .context/MEMORY.md
# Commit with descriptive message
git commit -m "$(cat <<'EOF'
Add explorer improvement plan and update memory
- Created comprehensive explorer improvement plan (Phase 1-4)
- Updated MEMORY.md with session decisions
Co-Authored-By: Swarm <[email protected]>
EOF
)"
Rules:
- Never use
git add -Aorgit add .without reviewing first - Never commit
.env, credentials, or large binaries - Always include
Co-Authored-Bywhen agent writes the commit - Prefer specific file staging over wildcard
- Ask user before committing if changes are large or unclear
Log & History
# Recent commits
git log --oneline -10
# Commits with file changes
git log --oneline --name-only -5
# Commits by date range
git log --since="2026-03-14" --until="2026-03-15" --oneline
# Search commit messages
git log --all --grep="keyword" --oneline
# Search code changes (pickaxe)
git log -S "function_name" --oneline
# File history
git log --oneline -- path/to/file
# Graph view
git log --oneline --graph --all -20
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.
- 6d ago First seen · 204 lines · 70 tokens per session scan A d2c6038a7156
workspace-git is a skill published in the GitHub repository xg-gh-25/SwarmAI (44 stars, last pushed 2d ago), licensed MIT. It adds 70 tokens to every session and 1,426 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
git-advanced-workflows
Master advanced Git workflows including rebasing, cherry-picking, bisect, worktrees, and reflog to maintain clean history and recover from any situation. Use when managing complex Git histories, collaborating on feature branches, or troubleshooting repository issues.
workflow-patterns
Use this skill when implementing tasks according to Conductor's TDD workflow, handling phase checkpoints, managing git commits for tasks, or understanding the verification protocol.
gsd-quick
Execute a quick task with GSD guarantees (atomic commits, state tracking) but skip optional agents.
gsd-quick-batch
Batch several /gsd:quick-shaped tasks together — planned, dispatched, and merged as one run.
gsd-pause-work
Create context handoff when pausing work mid-phase.
gsd-ship
Create PR, run review, and prepare for merge after verification passes.