multi-agent-system-pattern: Skill for Cursor

.cursor/skills/hitl-side-effects/SKILL.md

hitl-side-effects is a skill for Cursor from vpeetla-ai/multi-agent-system-pattern. It costs 47 tokens per session (291 once invoked), scanned A, original, MIT.

A set of patterns for requiring human approval before an agent performs an irreversible action, such as publishing, notifying someone, merging code, or pushing a pull request.

In plain words
What is it for?
Use it to build approval queues, review screens, pause-and-resume workflows, and human checkpoints before external side effects.
Why use it?
It prevents an agent from completing high-impact actions automatically and gives a person a chance to inspect what will happen and why.

Skill for Cursor

Written for Cursor: installed under .cursor/.

This is vpeetla-ai/multi-agent-system-pattern's own configuration. It tells Cursor how to work on multi-agent-system-pattern itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything multi-agent-system-pattern configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vpeetla-ai/multi-agent-system-pattern. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/vpeetla-ai/multi-agent-system-pattern/main/.cursor/skills/hitl-side-effects/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/vpeetla-ai/multi-agent-system-pattern

Made for: Cursor.

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 hitl-side-effects

README.md
[![agentmods](https://agentmods.dev/badge/skills/vpeetla-ai/multi-agent-system-pattern/hitl-side-effects.svg)](https://agentmods.dev/skills/vpeetla-ai/multi-agent-system-pattern/hitl-side-effects)
Your own site
<a href="https://agentmods.dev/skills/vpeetla-ai/multi-agent-system-pattern/hitl-side-effects"><img src="https://agentmods.dev/badge/skills/vpeetla-ai/multi-agent-system-pattern/hitl-side-effects.svg" alt="Measured on agentmods" height="20"></a>
Per session 47 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 291 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 $0.00047 $0.00291
Opus 5 $0.00023 $0.00146
Sonnet 5 $0.00009 $0.00058
Haiku 4.5 $0.00005 $0.00029

Measured 8d ago against content hash 46206f1cb94b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

hitl-side-effects 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 8d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.cursor/skills/hitl-side-effects/SKILL.md · 44 lines

What it actually says

HITL for Side Effects

LangGraph pattern

graph.compile(checkpointer=MemorySaver(), interrupt_before=["hitl"])
# First invoke stops before hitl node
# After human approval:
await graph.ainvoke({"hitl_approved": True}, config)

AegisAI pattern

  • POST /api/gateway/tool-requestpending | approved | denied
  • UI polls or webhook; agent resumes on approval

Content Factory

  • Draft → review queue → human edit → publish (gateway-wrapped)

LoopForge repo-fix

  • interrupt_before=["hitl"] before push/PR when create_pr=true
  • POST /api/repo-fix/{run_id}/approve resumes graph

UX requirements

  • Show what will happen (diff, channel, recipient)
  • Show why agent chose this action (trace excerpt)
  • Approve / Reject / Edit-and-approve

Never

  • Auto-approve production side effects without explicit env flag
  • Skip audit log on approval/denial
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. 8d ago First seen · 44 lines · 47 tokens per session scan A 46206f1cb94b

Subscribe to this mod's changes

hitl-side-effects is a skill published in the GitHub repository vpeetla-ai/multi-agent-system-pattern (2 stars, last pushed 3d ago), licensed MIT. It adds 47 tokens to every session and 291 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.

Related

Other skills, from other repositories

spec-polish

Start the dev server, inspect the feature in browser, and iterate on polish.

ronronner02/codepilot-agent · 20 tokens

remember

Review the current conversation and capture valuable knowledge — best practices, coding conventions, architecture decisions, workflows, and user feedback — into persistent memory (AGENTS.md) or reusable skills. Use when the user says: (1) remember this, (2) save what we learned, (3) update memory, (4) capture…

langchain-ai/deepagents · 71 tokens

deepagents-thread-inspector

Inspect and explain conversations in the local Deep Agents Code SQLite session store. Use as a fallback when LangSmith trace tooling is unavailable, for offline or untraced sessions, or when asked to identify or summarize a local dcode thread, inspect checkpoint metadata, list recent local threads, or parse…

langchain-ai/deepagents · 82 tokens

query-writing

Writes and executes SQL queries from simple SELECTs to complex multi-table JOINs, aggregations, and subqueries. Use when the user asks to query a database, write SQL, run a SELECT statement, retrieve data, filter records, or generate reports from database tables.

langchain-ai/deepagents · 57 tokens

planning

Break down a coding task into a structured implementation plan with clear steps, file identification, and risk assessment.

langchain-ai/deepagents · 23 tokens

python-package-management

Guide for managing packages in the Agent Framework Python monorepo, including creating new connector packages, versioning, and the lazy-loading pattern. Use this when adding, modifying, or releasing packages.

microsoft/agent-framework · 43 tokens