Skip to content
Agentmart
Submit a tool

hf-l2-delegation-gates

Enforce pre-delegation authorization gates before agent dispatch.

Skill by shynlee04

IndexedMIT★ 51
Write a review

Chalk Labs

Need help deploying hf-l2-delegation-gates?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/shynlee04-hf-l2-delegation-gates

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Enforce pre-delegation authorization gates before agent dispatch. Use when setting up checkpoint gates, defining capability matrices, validating agent permissions, or approving a handoff boundary. NOT for orchestration execution, direct implementation, or generic task planning.

Use cases: productivity, agent-building

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Nov 1, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found
Runs as
Shell scripts

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/hf-l2-delegation-gates

What's inside

Skill name
hf-l2-delegation-gates
Description
Enforce pre-delegation authorization gates before agent dispatch. Use when setting up checkpoint gates, defining capability matrices, validating agent permissions, or approving a handoff boundary. NOT for orchestration execution, direct implementation, or generic task planning.
License
MIT
Metadata
role: domain-execution · layer: domain-execution · pattern: P2
Instructions
273 lines in SKILL.md · view on GitHub

Before installing

  • Ships executable scripts

Agent Skills spec issues

  • allowed-tools: must be a space-separated string

Files (8)

  • SKILL.md
  • evals.json · evals/
  • rich-gate-scorecard.md · metrics/
  • boundary-guardrails.md · references/
  • gates.md · references/
  • rich-resource-rationale.md · references/
  • check-overlaps.sh · scripts/
  • validate-skill.sh · scripts/

SKILL.md (first lines)

## 6-NON Defence Table

| NON | Defence |
|-----|---------|
| NON-1 | Pre-authoring audit documented in references/ |
| NON-2 | Stacks/clashes documented in Cross-References |
| NON-3 | Entry trigger, exit criterion, and loop-back path defined |
| NON-4 | metadata.layer and metadata.role declared; description has exclusions |
| NON-5 | Eval includes stacked scenario |
| NON-6 | Pattern decision documented; scripts have non-zero exit |


<files_to_read>
.opencode/skills/hf-delegation-gates/references/gates.md
.opencode/skills/hf-delegation-gates/references/boundary-guardrails.md
.opencode/skills/hf-delegation-gates/references/rich-resource-rationale.md
</files_to_read>

# Agent Authorization Framework

## First Action

When a user requests agent authorization, immediately load `references/gates.md` for the gate structure and specialist profiles plus `references/boundary-guardrails.md` for child/tool/human boundary checks. Run the authorization checklist before proceeding.

## Authorization Workflow

```
[Task Request] → [Gate 1: Skills Check] → [Gate 2: Specialist Check] → [Gate 3: Capability Match] → [Gate 4: Scope Definition] → [Checkpoint: Human Verify] → [Agent Creation]
```

## Phase 30 Boundary Guardrails

Delegation gates are boundary checks, not just pre-flight checklists. Adapted from OpenAI guardrail tripwires and Claude hook lifecycle events, authorization must distinguish:

| Boundary | Required gate evidence |
|----------|------------------------|
| Workflow boundary | User intent, loaded skills, specialist availability, capability fit, scope document. |
| Child boundary | Handoff metadata: source agent, target agent, reason, allowed destinations, expected return. |
| Tool boundary | Permission/tool profile matches the child scope before mutation. |
| Human boundary | Checkpoint includes options, required response shape, and resume pointer. |

If any boundary is missing evidence, block before dispatch. Do not rely on final review to catch a bad handoff.

### Authorization Checklist

Complete each gate before proceeding to the next:

- [ ] **Gate 1:** Sufficient skills loaded for the task domain (typically 2-4)
- [ ] **Gate 2:** At least 2 specialist subagents available for the task domain
- [ ] **Gate 3:** Task matches specialist capabilities
- [ ] **Gate 4:** File paths and scope defined
- [ ] **Boundary:** Handoff metadata and allowed destinations defined
- [ ] **Boundary:** Tool/permission profile matches scope
- [ ] **Checkpoint:** Human verification (for blocking gates)

## Gate Definitions

### Gate 1: Skills Loaded Check

**Purpose:** Ensure the session has enough context to author an agent.

**Criteria:**
- Sufficient skills loaded from `.opencode/skills/` for the task domain (typically 2-4)
- Skills cover the relevant domain for the task

**If Gate 1 fails:**
```
⚠️ GATE 1 BLOCKED: Insufficient skills loaded
Required: Sufficient skills for task domain (typically 2-4)
Loaded: {count}
Action: Load additional skills before proceeding
```

### Gate 2: Specialist Availability Check

**Purpose:** Verify specialist subagents are available for the task domain.

**Criteria:**
- At least 2 specialist profiles defined for the task domain
- Specialists match task requirements

**If Gate 2 fails:**
```
⚠️ GATE 2 BLOCKED: Insufficient specialists available
Required: At least 2 specialists for task domain
Available: {count}
Action: Define additional specialist profiles
```

### Gate 3: Capability Match Check

**Purpose:** Ensure the task aligns with specialist capabilities.

**Criteria:**
- Task intent matches at least one specialist profile
- No capability gaps in the delegation chain

**If Gate 3 fails:**
```
⚠️ GATE 3 BLOCKED: Task capability mismatch
Task: {task_description}
Specialists: {specialist_list}
Action: Refine task scope or define new specialist profile
```

### Gate 4: Scope Definition Check

**Purpose:** Confirm file paths and task boundaries are defined.

**Criteria:**
- Target file paths identified
- Task scope written in a scope document (conventionally `.hivemind/state/planning/<session-id>/task_plan.md` if `hm-planning-persistence` is loaded, or any documented scope file)

**If Gate 4 fails:**
```
⚠️ GATE 4 BLOCKED: Scope not defined
Required: File paths + task scope in a scope document (conventionally task_plan.md)
Action: Document scope before proceeding
```

From shynlee04/hivemind-plugin, MIT.

More from shynlee04/hivemind-plugin

Signals

Stars
51
Forks
16
Open issues
21
Last commit (this folder)
May 7, 2026 (5 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from shynlee04

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get hf-l2-delegation-gates running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying hf-l2-delegation-gates?

CallGet help
Cite this page

hf-l2-delegation-gates skill. Agent Mart. https://agentmart.dev/skills/shynlee04-hf-l2-delegation-gates (last updated 2026-10-24)