DashClaw: Skill for Claude Code

.claude/skills/dashclaw-agent/manage-approvals/SKILL.md

manage-approvals is a skill for Claude Code from ucsandman/DashClaw. It costs 15 tokens per session (1,172 once invoked), scanned A, original, MIT.

A human-review workflow for approving or denying actions proposed by coding agents before they run. It supports review through a dashboard, command line, or software interface.

In plain words
What is it for?
Reviewing pending agent actions, approving or rejecting them with reasons, and monitoring requests that require approval.
Why use it?
It stops actions that need oversight until a person checks their purpose, risk, and affected systems.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Claude Code.

This is ucsandman/DashClaw's own configuration. It tells Claude Code how to work on DashClaw 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 DashClaw configures →

Reuse

Borrowing it

Nothing to install: this file belongs to ucsandman/DashClaw. 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/ucsandman/DashClaw/main/.claude/skills/dashclaw-agent/manage-approvals/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/ucsandman/DashClaw

Made for: Claude Code.

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 manage-approvals

README.md
[![agentmods](https://agentmods.dev/badge/skills/ucsandman/dashclaw/manage-approvals/github.svg)](https://agentmods.dev/skills/ucsandman/dashclaw/manage-approvals)
Your own site
<a href="https://agentmods.dev/skills/ucsandman/dashclaw/manage-approvals"><img src="https://agentmods.dev/badge/skills/ucsandman/dashclaw/manage-approvals/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.

agentmods 80×15 button for manage-approvals

Your own site · 80×15
<a href="https://agentmods.dev/skills/ucsandman/dashclaw/manage-approvals"><img src="https://agentmods.dev/badge/skills/ucsandman/dashclaw/manage-approvals.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,172 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 88
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 $0.00015 $0.01172
Opus 5 $0.00008 $0.00586
Sonnet 5 $0.00003 $0.00234
Haiku 4.5 $0.00002 $0.00117

Measured 9d ago against content hash 08cf761ef857, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

manage-approvals scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST "$DASHCLAW_BASE_URL/api/approvals/act_abc123" \
Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.claude/skills/dashclaw-agent/manage-approvals/SKILL.md · 155 lines

How it starts

The opening of the file, as written. The whole thing — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Manage Approvals

DashClaw's HITL (Human-in-the-Loop) system lets operators approve or deny agent actions before they execute. Three channels: dashboard, CLI, and SDK polling.

When Approvals Trigger

Approvals are triggered when:

  1. A guard policy returns require_approval
  2. An action's risk score exceeds the org's approval threshold
  3. The action touches systems flagged for mandatory review

The action enters pending_approval status and the agent waits.

Approval Channels

1. Dashboard (Web UI)

Navigate to the DashClaw dashboard → Approvals or Decisions view. Pending approvals show with:

  • Action type and declared goal
  • Agent ID
  • Risk score (color-coded)
  • Systems touched
  • Replay link for full decision context

Click Approve or Deny with optional reasoning.

2. CLI (Terminal)

# Interactive inbox — live updates via SSE
dashclaw approvals

# Direct approve/deny
dashclaw approve act_abc123 --reason "Reviewed deployment plan"
dashclaw deny act_abc123 --reason "Missing staging verification"

The interactive inbox (dashclaw approvals) uses SSE for real-time push notifications. New approval requests appear immediately without polling.

Keyboard shortcuts:

  • A — Approve selected
  • D — Deny selected
  • R — Refresh
  • O — Open replay in browser
  • Q — Quit

3. SDK Polling (Agent-Side)

// Agent waits for approval after guard returns require_approval
try {
  await claw.waitForApproval(decision.action_id, {
    timeout: 300000  // 5 minutes
  });
  console.log('Approved — proceeding');
} catch (err) {
  if (err instanceof ApprovalDeniedError) {
    console.log('Denied:', err.message);
    return;
  }
  throw err;
}
try:
    claw.wait_for_approval(decision["action_id"], timeout=300000)
    print("Approved — proceeding")
except ApprovalDeniedError as e:
    print(f"Denied: {e}")
    return

4. API Direct

# Approve
curl -X POST "$DASHCLAW_BASE_URL/api/approvals/act_abc123" \
  -H "x-api-key: $DASHCLAW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"decision": "approved", "reasoning": "Reviewed and safe"}'

# Deny
curl -X POST "$DASHCLAW_BASE_URL/api/approvals/act_abc123" \
  -H "x-api-key: $DASHCLAW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"decision": "denied", "reasoning": "Risk too high"}'

Read the full file on GitHub · 155 lines

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. 9d ago First seen · 155 lines · 15 tokens per session scan A 08cf761ef857

Subscribe to this mod's changes

manage-approvals is a skill published in the GitHub repository ucsandman/DashClaw (299 stars, last pushed 2d ago), licensed MIT. It adds 15 tokens to every session and 1,172 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.