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 asamassekou10/ship-safe --skill ship-safe-hooksgit clone --depth 1 https://github.com/asamassekou10/ship-safeWrote 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/asamassekou10/ship-safe/ship-safe-hooks)<a href="https://agentmods.dev/skills/asamassekou10/ship-safe/ship-safe-hooks"><img src="https://agentmods.dev/badge/skills/asamassekou10/ship-safe/ship-safe-hooks/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/asamassekou10/ship-safe/ship-safe-hooks"><img src="https://agentmods.dev/badge/skills/asamassekou10/ship-safe/ship-safe-hooks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 9 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 Agent Snooping · line 42 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 51 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 63 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 66 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 66 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- medium MCP Rug Pull · line 26 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 31 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium MCP Rug Pull · line 36 npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.Fix: Pin the version: npx @scope/[email protected]
- medium Rogue Agent · line 45 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00041 | $0.00640 |
| Opus 5 | $0.00020 | $0.00320 |
| Sonnet 5 | $0.00008 | $0.00128 |
| Haiku 4.5 | $0.00004 | $0.00064 |
Grade A, and why
ship-safe-hooks scanned grade A with 2 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 12d 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.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- To see what was installed: `cat ~/.claude/settings.json` Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- **Block** `Bash` calls matching dangerous patterns (curl piped to shell, credential exfiltration) How it starts
The opening of the file, as written. The whole thing — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship Safe — Claude Code Hooks
You are installing ship-safe as real-time security hooks into Claude Code. Once installed, ship-safe will:
- Block
Write/Edit/MultiEditcalls that contain critical secrets (API keys, tokens, private keys) before they are written to disk - Block
Bashcalls matching dangerous patterns (curl piped to shell, credential exfiltration) - Scan every file after it is written and inject advisory findings directly into this conversation
- Show a local
Protected by Ship Safestatus line in Claude Code when both hooks are ready
Step 1: Determine the action
If $ARGUMENTS is remove: run the remove command below.
If $ARGUMENTS is status: run the status command below.
Otherwise (default or install): run the install command.
Step 2: Run the command
Install (default):
npx ship-safe@latest hooks install
Remove:
npx ship-safe@latest hooks remove
Status check:
npx ship-safe@latest hooks status
Step 3: Report the result
On install success:
- Confirm that two hooks are now registered in
~/.claude/settings.json - Confirm that the Ship Safe status line is registered as well, unless another status line already exists
- Explain what each hook does:
- PreToolUse (on Write / Edit / MultiEdit / Bash): blocks critical secrets and dangerous commands in real time
- PostToolUse (on Write / Edit / MultiEdit): scans the written file and reports findings in context
- Tell the user that no restart is needed — hooks take effect immediately
- The status line is a local indicator backed by the installed hooks; it is not a decorative claim
On remove success:
- Confirm the hooks were removed from
~/.claude/settings.json
On status:
- Report which hooks are installed (✔) and which are missing (✗)
- If any are missing, offer to run
install
On error:
- If the command fails, check whether Node.js 18+ is available:
node --version - If hook scripts are missing, suggest reinstalling:
npm install -g ship-safe
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.
- 12d ago First seen · 67 lines · 41 tokens per session scan A 0129abded652
ship-safe-hooks is a skill published in the GitHub repository asamassekou10/ship-safe (842 stars, last pushed 5d ago), licensed MIT. It adds 41 tokens to every session and 640 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
security-review
Security audit focused on OWASP Top 10 — injection, auth flaws, secrets exposure, IDOR, and more. Use when reviewing code for vulnerabilities, before deploying to production, or auditing a new codebase.
security-audit
Audit code and infrastructure for security vulnerabilities. Use when performing security reviews, checking for OWASP Top 10 issues, auditing dependencies, or hardening applications.
depsguard
Install and run DepsGuard, a zero-dependency CLI that scans and fixes package manager configs (npm, pnpm, yarn, bun, uv) for supply chain security best practices.
optimize-cc-md
Interactively helps users optimize their CLAUDE.md files. Use when user asks to "optimize my CLAUDE.md", "my CLAUDE.md is too long", "improve organization", or "split my CLAUDE.md". Runs validation, explains issues conversationally, and helps create @import files to reduce size and improve structure.
skillpm
Manage npm-distributed Agent Skill packages with skillpm.
validate-cc-md
Validates CLAUDE.md files for size, imports, and structure. Use when user asks to "check my CLAUDE.md", "why is my CLAUDE.md too long", "validate imports", or "fix CLAUDE.md errors". Checks file size limits (30KB warning, 50KB error), @import directives, frontmatter in .claude/rules/, and section organization.