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 elliottwaves-20/agent-guard --skill agent-guardgit clone --depth 1 https://github.com/elliottwaves-20/agent-guardWrote 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/elliottwaves-20/agent-guard/agent-guard)<a href="https://agentmods.dev/skills/elliottwaves-20/agent-guard/agent-guard"><img src="https://agentmods.dev/badge/skills/elliottwaves-20/agent-guard/agent-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/elliottwaves-20/agent-guard/agent-guard"><img src="https://agentmods.dev/badge/skills/elliottwaves-20/agent-guard/agent-guard.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00430 | $0.08681 |
| Opus 5.5 | $0.00172 | $0.03472 |
| Sonnet 5.5 | $0.00086 | $0.01736 |
| Haiku 4.5 | $0.00043 | $0.00868 |
Grade C, and why
agent-guard scanned grade C with 5 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Downloads and executes remote codemediumSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
`curl | bash` install scripts and cargo crate sources. Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
find "$HOME/.claude/plugins/cache" -name "SKILL.md" -not -path "*/node_modules/*" \ Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Enumerates other installed skillslowAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
find "$HOME/.claude/skills" -maxdepth 2 -name "SKILL.md" \ Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Recursive force deletemediumDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$WORKDIR" 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.
malcontent), curl|bash install scripts via the SkillSpector static scan. Use How it starts
The opening of the file, as written. The whole thing — 694 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agent-guard — scan first, install after
Scanner setup is an explicit bootstrap trust decision by the operator. The setup scripts install trusted scanner tools and dependencies before any target can be scanned; they do not constitute a prior security verdict for the toolchain. Review setup separately. The scan-first workflow below applies to target skills and packages, not to automatically provisioning the scanner. Git installation requires the full scanned commit SHA. Package installation examples require substituting the exact scanned package version; bare example names are not installation approval. Existing destinations must be scanned directly before reuse; the installer never silently substitutes their contents.
Skills and MCP servers are third-party code that runs with your user account's
permissions. A malicious one can read SSH keys, .env files, and browser
profiles, exfiltrate them, or hijack the agent itself through a poisoned
SKILL.md. This skill makes a security scan the mandatory first step of every
installation.
Because skills follow the open SKILL.md standard and MCP is an open protocol, the scan is agent-agnostic: one verdict covers Claude Code, Codex, Antigravity, Gemini CLI, Hermes, OpenClaw, and any other compatible agent — and the installer deploys the same audited commit to all of them in one step.
Professional scanners do the work, each where it is strongest:
- NVIDIA SkillSpector — skill
scans and the static MCP source scan. One tool for both, with 71
vulnerability patterns (prompt injection, data exfiltration, privilege
escalation, MCP tool poisoning / least-privilege, supply chain with live
OSV.dev CVE lookup, bundled hooks/settings), taint tracking, YARA,
hidden/nested-archive inspection, and LLM analysis through the user's own
coding-agent CLI login (no API key) or a hosted provider. Also covers
curl | bashinstall scripts and cargo crate sources. - cisco-ai-mcp-scanner —
the optional live runtime MCP check (
scan_mcp.py --sandbox/remote). A static scan cannot see MCP tools that a server only registers at runtime; this starts the server in a sandbox to inspect them. - Datadog GuardDog — CLI-tool
package scans (npm/PyPI/Go/cargo) via
scan_cli.py; malware heuristics + YARA + registry metadata, run through the official Docker image on Windows. - VirusTotal + malcontent
— release binaries via
scan_cli.py binary: hash reputation, optionally (--deep) a capability analysis.
What ships with it
41 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- scripts/_cisco_boot.py 1.7 KB runs code
- scripts/_console.py 604 B runs code
- scripts/_distribution.py 6.3 KB runs code
- scripts/_dossier.py 5.7 KB runs code
- scripts/_dynamic.py 16 KB runs code
- scripts/_egress.py 14 KB runs code
- scripts/_explain.py 6.6 KB runs code
- scripts/_llm_adapter.py 9.8 KB runs code
- scripts/_llm_budget.py 14 KB runs code
- scripts/_llm_profile.py 12 KB runs code
- scripts/_parse_spans_boot.py 3.0 KB runs code
- scripts/_parse_spans.py 3.6 KB runs code
- scripts/_pins.py 1.2 KB runs code
- scripts/_providers.py 4.3 KB runs code
- scripts/_skills_cli.py 16 KB runs code
- scripts/_skillspector_boot.py 449 B runs code
- scripts/_skillspector.py 41 KB runs code
- scripts/_staging.py 17 KB runs code
- scripts/_triage.py 27 KB runs code
- scripts/_url_resolver.py 21 KB runs code
- scripts/_user_config.py 4.3 KB runs code
- scripts/_verifier_boot.py 1.3 KB runs code
- scripts/_verifier.py 14 KB runs code
- scripts/_yara_recheck_boot.py 3.4 KB runs code
- scripts/_yara_recheck.py 5.3 KB runs code
- scripts/audit_installed.py 20 KB runs code
- scripts/install_skill.py 40 KB runs code
- scripts/llm_check.py 7.8 KB runs code
- scripts/llm_scan.py 10 KB runs code
- scripts/reviewed/skills-cli-1.7.0.json 2.7 KB
- scripts/run_all_tests.py 5.7 KB runs code
- scripts/scan_cli.py 22 KB runs code
- scripts/scan_mcp.py 40 KB runs code
- scripts/scan_skill.py 6.3 KB runs code
- scripts/scan_url.py 32 KB runs code
- scripts/triage/destructive_commands.toml 873 B
- scripts/triage/known_noise.toml 2.9 KB
- scripts/triage/yara_corrections.toml 1.2 KB
- scripts/triage/yara_corrections.yar.b64 1.8 KB
- scripts/update_skills.py 23 KB runs code
- scripts/verify_skills_cli.py 4.9 KB runs code
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 Changed · +1 lines 73fdabd62466
- 9d ago Changed · +20 lines 9d64926705b0
- 15d ago Changed · +7 lines 0d8968ddc67f
- 16d ago Changed · +2 lines · +6 tokens per session bfa7811333b9
- 1mo ago Changed · +69 lines · +24 tokens per session 0a148db90c33
- 1mo ago Changed · +16 lines · +25 tokens per session 7bd8893cc912
- 2mo ago First seen · 579 lines · 375 tokens per session scan C e7a3fd3d8376
agent-guard is a skill published in the GitHub repository elliottwaves-20/agent-guard (5 stars, last pushed 5d ago), licensed MIT. It adds 430 tokens to every session and 8,681 once invoked, about $0.0017 per session on Opus 5.5. A static security scan graded it C with 5 findings (downloads and executes remote code, reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
clinical-trial-protocol-skill
Generate clinical trial protocols for medical devices or drugs. This skill should be used when users say "Create a clinical trial protocol", "Generate protocol for [device/drug]", "Help me design a clinical study", "Research similar trials for [intervention]", or when developing FDA submission documentation for…
agent-safety
Use when bounding an LLM agent that already runs — scoping its task domain, gating tools to least privilege, defending against prompt injection in untrusted web/email/RAG text, requiring human approval on irreversible actions, capping runtime and cost, or triaging what it already did. NOT building the loop, tools, or…
adr-skill
Create and maintain Architecture Decision Records (ADRs) optimized for agentic coding workflows. Use when you need to propose, write, update, accept/reject, deprecate, or supersede an ADR; bootstrap an adr folder and index; consult existing ADRs before implementing changes; or enforce ADR conventions. This skill uses…
prior-auth-review-skill
Automate payer review of prior authorization (PA) requests. This skill should be used when users say "Review this PA request", "Process prior authorization for [procedure]", "Assess medical necessity", "Generate PA decision", or when processing clinical documentation for coverage policy validation and authorization…
linear-claude-skill
Manage Linear issues, projects, and teams.
playwright-skill
IMPORTANT - Path Resolution: This skill can be installed in different locations (plugin system, manual installation, global, or project-specific). Before executing any commands, determine the skill directory based on where you loaded this SKILL.md file, and use that path in all commands below.