security-tiers

security-tiers is a skill for Claude Code from metraton/gaia. It costs 21 tokens per session (12,531 once invoked), scanned B, original, MIT.

A set of rules for classifying commands by security risk and deciding whether they can run immediately or need user approval. It applies to each individual command.

In plain words
What is it for?
Reviewing commands before execution, identifying operations that need approval, grouping only predictable related commands, and recording their rollback and verification details.
Why use it?
It makes command permissions explicit and prevents risky operations from being hidden inside broad or compound requests.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event. Also seen: reads .claude/ paths; mentions subagents; mentions Claude Code.

Part of the gaia plugin — 38 skills, 9 agents, 11 hooks shipped together

Good fit Reviewing commands before execution, identifying operations that need approval, grouping only predictable related commands, and recording their rollback and verification details.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/metraton/gaia/security-tiers
Install

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.

Any agent
npx skills add metraton/gaia --skill security-tiers
Clone the repo
git clone --depth 1 https://github.com/metraton/gaia

Made for: Claude Code.

Or install gaia, the plugin that ships this one along with the rest of its 38 skills, 9 agents, 11 hooks.

Wrote 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.

agentmods badge for security-tiers

README.md
[![agentmods](https://agentmods.dev/badge/skills/metraton/gaia/security-tiers/github.svg)](https://agentmods.dev/skills/metraton/gaia/security-tiers)
Your own site
<a href="https://agentmods.dev/skills/metraton/gaia/security-tiers"><img src="https://agentmods.dev/badge/skills/metraton/gaia/security-tiers/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.

agentmods 80×15 button for security-tiers

Your own site · 80×15
<a href="https://agentmods.dev/skills/metraton/gaia/security-tiers"><img src="https://agentmods.dev/badge/skills/metraton/gaia/security-tiers.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 12,531 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 3 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00021 $0.12531
Opus 5 $0.00010 $0.06266
Sonnet 5 $0.00004 $0.02506
Haiku 4.5 $0.00002 $0.01253

Measured 9d ago against content hash 2fed40d51803, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade B, and why

security-tiers scanned grade B with 3 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 9d 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.

**The rule applies to every execution path, not only deliberate edits.** A `sed -i`, `find -exec`, `xargs`, glob expansion, or any script that sweeps a directory tree is bound by exactly the same policy as a targeted `Ed

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.

- `flag_classifiers.py` -- `_classify_curl` / `classify_by_flags` detect flag-dependent mutations; triggers T3 on commands whose flags make them mutative (e.g., `curl -X POST`).

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- `mutative_verbs.py` -- CLI-agnostic detection of mutative verbs; drives the nonce / approval flow for T3. Includes script-file detection (Step 1d, `_check_script_file`): when a command is `<interpreter> <script-file>`
skills/security-tiers/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Tiers

COMMAND_SET boundary

Classification applies to each exact atomic command. After read-only investigation, one or more predictable T3 commands may be requested plan-first with gaia approvals request-set -- a single predictable T3 command uses the same verb proactively, not only the reactive path that begins after PreToolUse returns [T3_BLOCKED]. Never discover a set by attempting a compound shell command. Group only one bounded goal with exact known order and coherent risk, rollback, and verification. Those last two are supplied on the request itself -- --rollback and --verification, alongside --rationale and one --command per item -- and are sealed at mint, then rendered verbatim as the ROLLBACK and VERIFICATION fields of the surface the user consents against; requesting without them asks for consent while the surface states they are absent. Do not group speculative or output-dependent steps. Consent grouping is not execution atomicity: execution remains one command per call, ordered and fail-fast.

security-tiers classifies every operation into four tiers so an agent knows whether it can run freely or must request the user's consent.

The four tiers

Tier What it is Approval? Example verbs
T0 Read-only; observes state, changes nothing No get, list, describe, show, logs, status
T1 Local validation; no remote calls, no state No validate, lint, fmt, check
T2 Simulation / dry-run; may read remote, never writes No plan, diff, dry-run, template
T3 State-mutating; creates, updates, or destroys Yes apply, create, delete, push, deploy

A fifth verdict exists OUTSIDE this ladder: the categorical denial -- blocked commands, the .claude/hooks tree targeted through Bash (hooks/modules/security/protected_path_guard.py::check), the DB-write guards, and a file write into a git working tree whose author is the SHELL (hooks/modules/security/shell_write_guard.py::check). It is not a tier, it is not approvable, and no grant lifts it.

Read the full file on GitHub · 124 lines

Files

What ships with it

2 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.

Changes

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.

  1. 9d ago First seen · 124 lines · 21 tokens per session scan B 2fed40d51803

Subscribe to this mod's changes

security-tiers is a skill published in the GitHub repository metraton/gaia (3 stars, last pushed yesterday), licensed MIT. It adds 21 tokens to every session and 12,531 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 3 findings (reads agent configuration directories, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories