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/codeinfinity1/stram/approval-gated-external-actionsnpx skills add CodeInfinity1/Stram --skill approval-gated-external-actionsgit clone --depth 1 https://github.com/CodeInfinity1/StramWrote 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/codeinfinity1/stram/approval-gated-external-actions)<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="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 | $0.00033 | $0.00406 |
| Opus 5 | $0.00016 | $0.00203 |
| Sonnet 5 | $0.00007 | $0.00081 |
| Haiku 4.5 | $0.00003 | $0.00041 |
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 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
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_describechannel_message_preparechannel_message_sendlobster_workflow_startlobster_workflow_approvemessage-approval-policy
Workflow
- Identify whether action is external, irreversible, costly, destructive, or privacy-sensitive.
- Prepare/review exact payload before execution.
- Request approval through the native tool/workflow path.
- Execute only after approval.
- Verify final status.
- 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.
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 · 66 lines · 33 tokens per session scan A d624649c1f69
approval-gated-external-actions is a skill published in the GitHub repository CodeInfinity1/Stram (10 stars, last pushed 24d ago), licensed MIT. It adds 33 tokens to every session and 406 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 2026-08-31.
Other skills, from other repositories
golden-rss
Use when testing the rss golden build.
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.
verify
Fact-check claims encountered during reading — dates, names, events, citations. Use when encountering historical facts or disputed claims.
bailian-docs-llm-wiki
阿里云百炼平台技术文档知识库（LLM Wiki）。当用户查询百炼模型列表、API 参数、错误码、 应用开发（智能体/RAG/知识库/记忆/插件）、模型对比与定价、SDK/OpenAI 兼容接口、 多模态能力（语音/图片/视频）、Token 计费等百炼相关问题时激活。 包含 models 结构化模型市场数据（含 contextWindow/QPM/价格/sample code）、 wiki 合成层（主题页/概念页/对比页）和 raw 原始文档层； 模型规格类问题先查 models/index.md，文档类问题先查 wiki/index.md。.
write-blog-post
Write or develop a blog post. Use for blog content - writing, drafting, developing ideas into drafts, or editing. Longer-form than LinkedIn (800-1200 words) with section structure.
spec
Draft a Workflow Phase 4 technical spec from an intake (and optionally a BRD + scout + research memo). The spec defines how the system will change: design (C4 + UML + dependency graph in PlantUML), data, APIs, tests, rollout, rollback. Output lives at docs/specs/ .md. Never self-approves — approval happens via…