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 skills add seb1n/awesome-ai-agent-skills --skill human-in-the-loopgit clone --depth 1 https://github.com/seb1n/awesome-ai-agent-skillsWrote 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/seb1n/awesome-ai-agent-skills/human-in-the-loop)<a href="https://agentmods.dev/skills/seb1n/awesome-ai-agent-skills/human-in-the-loop"><img src="https://agentmods.dev/badge/skills/seb1n/awesome-ai-agent-skills/human-in-the-loop/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.
<a href="https://agentmods.dev/skills/seb1n/awesome-ai-agent-skills/human-in-the-loop"><img src="https://agentmods.dev/badge/skills/seb1n/awesome-ai-agent-skills/human-in-the-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00072 | $0.01908 |
| Opus 5 | $0.00036 | $0.00954 |
| Sonnet 5 | $0.00014 | $0.00382 |
| Haiku 4.5 | $0.00007 | $0.00191 |
Grade A, and why
human-in-the-loop 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 12d 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.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Human in the Loop
Place human judgment at the decision point where it changes risk. A confirmation dialog alone is not oversight: bind an authorized decision to an understandable, immutable action and preserve evidence of what happened.
Inputs
Collect or infer, and label assumptions for:
- Agent goal, workflow states, and every action it can propose or execute
- Effect type, reversibility, value, affected people, and worst credible impact
- Data sensitivity, regulatory or contractual duties, and organizational risk tolerance
- Stable requester and approver subject identities, role assignments, policy owner, separation-of-duties rules, and coverage hours
- Required response time, timeout behavior, escalation contacts, and availability target
- Evidence an approver needs, including provenance, uncertainty, and alternatives
- Existing identity, policy, audit, ticketing, and notification systems
- Failure, retry, cancellation, compensation, and incident paths
Do not invent approver authority or organizational policy. If missing information affects a consequential action, produce a proposed policy and mark it for owner approval.
Output contract
Deliver:
- An action inventory and rationale-backed risk tier for each action
- A gate policy defining validated predicates, eligible approver roles and distinct subjects, quorum, evidence, expiry, timeout, structured escalation, audit-outage behavior, execution-time reauthorization, compensation, break-glass, and separation of duties
- A state machine for prepare, review, decision, execution, failure, and recovery
- An approval experience that shows the exact action, material effects, uncertainty, provenance, alternatives, and safe reject/edit paths
- An append-only decision record schema and retention/redaction requirements
- Implementation or a file-level plan, plus policy and concurrency tests
- Verification evidence, unresolved policy decisions, residual risk, and an operational recovery plan
Start from assets/approval-policy-template.json when a machine-readable policy helps. Validate it with scripts/validate_gate_policy.py. Read references/gate-design-guide.md for risk-tier and state-machine guidance.
What ships with it
4 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.
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.
- 12d ago First seen · 137 lines · 72 tokens per session scan A 4228420ef0d7
human-in-the-loop is a skill published in the GitHub repository seb1n/awesome-ai-agent-skills (179 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 1,908 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
cross-border-ecommerce
Cross-border e-commerce expansion advisor. Scores target markets on 8 weighted dimensions (market size, ecommerce penetration, competition, regulatory complexity, logistics infrastructure, payment ecosystem, cultural distance, IP protection), compares 5 fulfillment models with cost and transit data, provides…
ecommerce-email-marketing-builder
E-commerce email marketing system builder. Creates complete email automation flows with full copywriting, subject lines, ESP setup instructions, segmentation rules, and annual campaign calendars. Generates copy-paste-ready email sequences for Klaviyo, Omnisend, Mailchimp, or any ESP. Covers welcome series, cart…
ecommerce-content-marketing
E-commerce content marketing strategy planner. Generates content calendars, topic ideas, and platform-specific strategies by analyzing customer reviews, trends, competitor content, and SEO opportunities. Two modes: (A) Build — create a full content strategy from scratch, (B) Audit — analyze existing content and find…
ecommerce-growth-strategy
E-commerce growth strategy advisor. Diagnoses current business health using unit economics (CAC, LTV, AOV, contribution margin), identifies the highest-impact growth opportunities across 5 levers (traffic, conversion, AOV, retention, expansion), and builds a prioritized 90-day growth roadmap. Uses the Ansoff Matrix…
ecommerce-marketing-strategy-builder
Full-stack e-commerce marketing strategy builder. Analyzes your product, market, and competitors, then builds a complete omnichannel marketing plan covering paid ads, SEO, email/SMS, content marketing, social media, influencer partnerships, and referral programs. Includes target audience persona, competitive…
ecommerce-ppc-strategy-planner
Cross-platform PPC strategy planner for ecommerce businesses. Analyzes your product and margins, recommends the right advertising platforms (Google Ads, Meta Ads, TikTok Ads), calculates ROAS targets, allocates budget across channels, and generates platform-specific campaign briefs with ad copy and creative direction.…