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/vpeetla-ai/react-agent-pattern/hitl-side-effectsnpx skills add vpeetla-ai/react-agent-pattern --skill hitl-side-effectsgit clone --depth 1 https://github.com/vpeetla-ai/react-agent-patternWrote 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/vpeetla-ai/react-agent-pattern/hitl-side-effects)<a href="https://agentmods.dev/skills/vpeetla-ai/react-agent-pattern/hitl-side-effects"><img src="https://agentmods.dev/badge/skills/vpeetla-ai/react-agent-pattern/hitl-side-effects.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 | $0.00047 | $0.00291 |
| Opus 5 | $0.00023 | $0.00146 |
| Sonnet 5 | $0.00009 | $0.00058 |
| Haiku 4.5 | $0.00005 | $0.00029 |
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 4d 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.
This is a copy
100% identical to hitl-side-effects — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
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-request→pending|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 whencreate_pr=truePOST /api/repo-fix/{run_id}/approveresumes 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
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.
- 4d ago First seen · 44 lines · 47 tokens per session scan A 46206f1cb94b
hitl-side-effects is a skill published in the GitHub repository vpeetla-ai/react-agent-pattern (2 stars, last pushed today), 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. It is 100% identical to hitl-side-effects, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
deploy-vercel-render
Deploy vpeetla-ai demos: Vercel static/Next.js frontends, Render FastAPI backends, env vars, free tier gotchas. Use when shipping demos, fixing deploy failures, or adding render.yaml / vercel.json.
langgraph-orchestration
Build or modify LangGraph StateGraph agents in vpeetla-ai repos: typed state, nodes, conditional edges, MemorySaver, interruptbefore HITL. Use when adding orchestrators, coding loops, or multi-agent graphs.
aegis-gateway
Integrate AegisAI gateway before tool side effects (notify, publish, deploy). Use when adding Slack/Telegram/WhatsApp notify, content publish, or any irreversible external action in VAP, AegisLoop, or ai-content-factory.
hitl-side-effects
Add human-in-the-loop gates for irreversible actions: LangGraph interruptbefore, AegisAI approval queue, UI approve/resume endpoints. Use when shipping, publishing, notifying, or merging agent-generated changes.
portfolio-adr
Write ADRs, case studies, and portfolio copy for ai-architecture-portfolio and venkat-ai-portfolio. Use when documenting decisions, updating ecosystem pages, or syncing GitHub profile README with live demos.
rag-governance
Implement access-aware RAG in Enterprise RAG or VAP: hybrid retrieval, rerank, citations, AegisAI HITL for sensitive chunks. Use when tuning retrieval, adding Qdrant adapter, or wiring enterpriseragplatform.