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 agentmods add skills/jeongjaesoon/agent-guard/setup-shellnpx skills add JeongJaeSoon/agent-guard --skill setup-shellgit clone --depth 1 https://github.com/JeongJaeSoon/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/jeongjaesoon/agent-guard/setup-shell)<a href="https://agentmods.dev/skills/jeongjaesoon/agent-guard/setup-shell"><img src="https://agentmods.dev/badge/skills/jeongjaesoon/agent-guard/setup-shell.svg" alt="Measured on agentmods" 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 | $0.00043 | $0.00452 |
| Opus 5 | $0.00022 | $0.00226 |
| Sonnet 5 | $0.00009 | $0.00090 |
| Haiku 4.5 | $0.00004 | $0.00045 |
Grade A, and why
setup-shell 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 3d 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.
What it actually says
Set Up Agent Guard Shell
Install or refresh Agent Guard shell command masking without making the user locate the versioned plugin-cache binary.
Workflow
-
Explain that this changes the user's shell rc and is separate from plugin hook setup.
-
Resolve
../../bin/agent-guardrelative to this skill directory and confirm that it is executable. Use that plugin-local binary even if anotheragent-guardis onPATH; do not install or update a standalone copy. -
Tell the user that
setup-shellwill update the managed block in their shell rc with command wrapping enabled by default. Obtain host approval for the home-directory write before running:"<plugin-local-agent-guard>" setup-shell -
On success, report every rc path from the command output and tell the user to restart the shell and any agent sessions launched from that shell. A fish login shell gets two rc files (the integration is POSIX shell code that fish cannot load, and agent shell snapshots run bash or zsh); relay the fish notice from the output as-is, including that no automatic
agxis installed at a fish prompt, a bareagent-guardmay be unavailable for plugin-only installs, and the command prints an executable path that works withoutPATH. -
If the approved write is blocked by the host sandbox, relay the exact error. Do not retry the same blocked write, choose another rc, or edit the rc by hand. Show the exact plugin-local command for the user to run directly in a terminal, wait for confirmation, and then report the required restarts.
Use setup-shell --no-command-wrapping only when the user explicitly requests
the persistent opt-out. AGENT_GUARD_COMMAND_WRAPPING=off is the runtime-only
opt-out.
What ships with it
1 file 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.
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.
- 3d ago First seen · 41 lines · 43 tokens per session scan A 9a3d293486fc
setup-shell is a skill published in the GitHub repository JeongJaeSoon/agent-guard (24 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 452 once invoked, about $0.0002 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
audit-production-readiness
Audit a repository or service for release-blocking bugs, security, data/privacy, AI-agent, supply-chain, operability, and scale risks. Use for deep code audits, threat models, pre-production reviews, vulnerability triage, incidents, defensive investigation, release gates, or evidence-based 10k-to-1M-user readiness.
engineer-production-systems
Design, write, refactor, or optimize production code so it is secure, correct, resource-bounded, observable, and maintainable. Use for full-stack features, APIs, databases, AI/RAG/MCP tools, CPU/RAM/latency work, 10k-to-1M-user planning, or authorized kernel, browser, parser, protocol, and defensive…
best-in-code
Run an adaptive, reusable software-delivery harness across AI models with project management, planning, research, design, frontend, backend, QA, durable scoped memory, capability fallbacks, bounded discovery, and human approval gates. Use when the user invokes Harness or asks for an end-to-end build, review, bug…
terraform-hardening
Use when changing or reviewing the Terraform-backed GitHub repository hardening workspace under config/infra, including provider pins, rulesets, default branch protection, required checks, secret scanning, Dependabot security updates, token handling, plan/apply behavior, and infra documentation. Do not use for…
github-hardening
Use when updating or reviewing GitHub-side hardening guidance for derived repositories, including required settings, rulesets, scanning, review protections, and workflow permissions. Use terraform-hardening instead for Terraform-backed changes under config/infra. Do not use for ordinary in-repo implementation changes…
language-profile-guidance
Use when adding or revising optional language-specific guidance for Go, Node.js, SQL, or small polyglot derived repositories without bloating the generic template. Keep language behavior optional. Do not use for generic template policy, routine validation, GitHub-settings-only work, or release-integrity-only work.