agentmods.dev

approval-gated-external-actions

approval-gated-external-actions is a skill for Claude Code, Codex from CodeInfinity1/Stram. It costs 33 tokens per session (406 once invoked), scanned A, original, MIT.

An approval policy for actions that can change external systems, spend money, send messages, install software, write files, or otherwise be hard to undo.

In plain words
What is it for?
Use it to prepare, request approval for, perform, and verify purchases, messages, installations, file changes, remote API updates, and public posts.
Why use it?
It keeps a person in control of high-impact actions by requiring the exact action and payload to be reviewed before execution.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 11repo 2mo ago A scan 33 tokens original MIT

Good fit Use it to prepare, request approval for, perform, and verify purchases, messages, installations, file changes, remote API updates, and public posts.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/codeinfinity1/stram/approval-gated-external-actions
View source ↗ CodeInfinity1/Stram
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 CodeInfinity1/Stram --skill approval-gated-external-actions
Clone the repo
git clone --depth 1 https://github.com/CodeInfinity1/Stram

Made for: Claude Code, Codex.

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 approval-gated-external-actions

README.md
[![agentmods](https://agentmods.dev/badge/skills/codeinfinity1/stram/approval-gated-external-actions/github.svg)](https://agentmods.dev/skills/codeinfinity1/stram/approval-gated-external-actions)
Your own site
<a href="https://agentmods.dev/skills/codeinfinity1/stram/approval-gated-external-actions"><img src="https://agentmods.dev/badge/skills/codeinfinity1/stram/approval-gated-external-actions/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 approval-gated-external-actions

Your own site · 80×15
<a href="https://agentmods.dev/skills/codeinfinity1/stram/approval-gated-external-actions"><img src="https://agentmods.dev/badge/skills/codeinfinity1/stram/approval-gated-external-actions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 406 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00033 $0.00406
Opus 5.5 $0.00013 $0.00162
Sonnet 5.5 $0.00007 $0.00081
Haiku 4.5 $0.00003 $0.00041

Measured 1mo ago against content hash d624649c1f69, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

approval-gated-external-actions 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.

skills/agent-core/approval-gated-external-actions/SKILL.md · 66 lines

What it actually says

Approval Gated External Actions

Purpose

Keep high-impact actions under human control. This skill applies the assistant's approval discipline across tools and workflows.

When To Use

Use before sending messages, buying anything, installing packages, pushing code, deleting files, changing apps, mutating APIs, or posting publicly.

Inputs And Evidence

  • Exact action, target, payload, risk, tool schema, approval token/status, and expected result.
  • Prior draft or prepared outbox item.

Tool Map

  • tool_describe
  • channel_message_prepare
  • channel_message_send
  • lobster_workflow_start
  • lobster_workflow_approve
  • message-approval-policy

Workflow

  1. Identify whether action is external, irreversible, costly, destructive, or privacy-sensitive.
  2. Prepare/review exact payload before execution.
  3. Request approval through the native tool/workflow path.
  4. Execute only after approval.
  5. Verify final status.
  6. Report blocked/pending states honestly.

Native Implementation Boundaries

  • Use Stram approval queue, risk levels, and workflow tools.
  • Do not import external reference AgentGate/AgentPay code.
  • Any new high-risk tool must be native and approval-gated.

Safety And Approval

  • Approval is specific to exact action and payload.
  • Edits after approval require re-review where risk changes.
  • Never blur prepared into sent/executed.

Verification

  • Approval records or tool status prove state.
  • Sent/executed claims require tool result.
  • Rejections should be honored.

Failure Modes

  • Auto-executing because the task seems obvious.
  • Changing payload after approval.
  • Claiming pending actions completed.

References

  • Shortlist item: approval-gated-external-actions.
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. 1mo ago First seen · 66 lines · 33 tokens per session scan A d624649c1f69

Subscribe to this mod's changes

approval-gated-external-actions is a skill published in the GitHub repository CodeInfinity1/Stram (11 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 406 once invoked, about $0.0001 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 2026-08-31.

Building agentsai-agentai-agentsai-toolsdesktop-automationdesktop-automation-softwaredesktop-automation-windows
Related

Other skills, from other repositories

android-pentest

A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.

Netw0rkNoob/VulnClaw · 32 tokens

lighting-report-extract

Check reported lighting quantities and results in supplied simulation PDFs without adding repeated calculation surfaces. Use for scoped luminaire inventories and illuminance results; not simulation or compliance.

AlpacaLabsLLC/skills-for-architects · 37 tokens

authentication-patterns

OAuth 2.0, JWT, SSO, MFA, NextAuth/Clerk/Supabase Auth implementation patterns.

travisjneuman/.claude · 28 tokens

container-debugging

Diagnose reported container build, startup, network, permission and resource failures. Use when an image or Compose service fails; reproduce against the final image/config and avoid data-destroying cleanup as a workaround.

WrongStack/WrongStack · 45 tokens

alive:system-upgrade

Upgrade ALIVE to the current version. Handles v1/v2/v3.x source states, multi-surface aware (alive-mcp / Hermes / Codex), retroactive version detection, partial-failure resume, dry-run previews, and rollback inspection.

alivecontext/alive · 57 tokens

pr-review

Comprehensive PR review across six dimensions — cost impact, environment drift, ownership gaps, SOC 2 compliance, deprecated API / version hygiene, and rollback feasibility. Each mode inspects the diff and current file state, reports findings with severity, and recommends concrete fixes. Use when preparing a PR for…

nitinjain999/platform-skills · 81 tokens