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 cwinvestments/memstack --skill git-guardgit clone --depth 1 https://github.com/cwinvestments/memstackWrote 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/cwinvestments/memstack/git-guard)<a href="https://agentmods.dev/skills/cwinvestments/memstack/git-guard"><img src="https://agentmods.dev/badge/skills/cwinvestments/memstack/git-guard/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/cwinvestments/memstack/git-guard"><img src="https://agentmods.dev/badge/skills/cwinvestments/memstack/git-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 121 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.
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 | $0.00092 | $0.03146 |
| Opus 5.5 | $0.00037 | $0.01258 |
| Sonnet 5.5 | $0.00018 | $0.00629 |
| Haiku 4.5 | $0.00009 | $0.00315 |
Grade A, and why
memstack-security-git-guard 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 — 307 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🛡️ Git-Guard: Verifying Repo Protection...
Install and verify the machine-wide secret-blocking setup on a repo. Confirms the global pre-commit hook, .gitignore coverage, a non-neutered gitleaks config, and a reachable gitleaks binary.
Activation
When this skill activates, output:
🛡️ Git-Guard: Verifying Repo Protection...
Then execute the protocol below.
What This Skill Is (and Is Not)
Git-Guard is an installer and verifier, not a scanner. It does not grep for secret patterns itself. Its job is to confirm that the protection layers are present, wired up, and actually armed, so that when a secret IS introduced, gitleaks (run by the pre-commit hook) catches it.
The single most dangerous failure this skill exists to catch is a gitleaks config that LOOKS protective but detects nothing (see Check 3). A scanner that silently scans zero rules is worse than no scanner, because it produces a green checkmark while leaving the door open.
Context Guard
| Context | Status |
|---|---|
| User asks "is this repo protected?" | ACTIVE: run all 4 checks |
| User says "set up / install git-guard" | ACTIVE: run checks, offer fixes |
| User says "verify gitleaks" / "check git hooks" | ACTIVE: run all 4 checks |
| New repo, before first commit | ACTIVE: install gitignore + verify config |
| User wants a deep secret/history audit | DORMANT: defer to secrets-scanner |
| User is mid-commit and just wants it to pass | DORMANT: do not loosen protection to unblock |
Protocol
Run all four checks (Steps 1 to 4), then produce the status report in Step 5. Step 5 is the report itself, not a fifth check. Never silently run a setup or fix command: show the exact command and let the user run it (or confirm first). The one exception is the additive .gitignore append in Check 2, which is safe and reversible and may be applied after showing the diff.
Locating the files shipped with this plugin
Two checks reference files that ship INSIDE this plugin: the pre-commit hook
and gitignore-template.txt, both under the plugin's scripts/ directory.
After install, those files live in the Claude Code plugin cache, NOT in any
fixed location, and NOT in the customer's own project. Resolve <plugin-root>
as the plugin folder this SKILL.md was loaded from, walking up out of
skills/security/git-guard/ to the folder that contains scripts/.
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 · 307 lines · 92 tokens per session scan A 78de28103b6f
memstack-security-git-guard is a skill published in the GitHub repository cwinvestments/memstack (425 stars, last pushed 3d ago), licensed MIT. It adds 92 tokens to every session and 3,146 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 2026-09-03.
Other skills, from other repositories
github-workflow
GitHub best practices for pull requests, code reviews, issues, Actions workflows, and repository management.
git-workflow
Git conventions and workflow guidelines using Conventional Commits, branching strategies, and best practices for version control.
lerna
Best practices for Lerna monorepo management, versioning, and publishing.
atomic-git-discipline
Compressed commit message and PR body generator. Cuts noise from both while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious; PR bodies state only what the diff can't show, 120 words max. Use when user says "write a commit", "commit message", "generate…
core-workflow
Detailed development workflow patterns, checklists, and standards. Auto-loads for complex tasks, planning, debugging, or when explicit patterns are needed. Contains session protocols, git conventions, security checklists, review-based validation, and communication standards.
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.