agent-approval-protocol

agent-approval-protocol is a skill for Claude Code from metraton/gaia. It costs 22 tokens per session (1,063 once invoked), scanned A, original, MIT.

A reference for passing approval requests safely between coding agents and the runtime that controls them. It defines the exact formats for agent identities, approval IDs, fingerprints, and progress information.

In plain words
What is it for?
Use it when an agent must request approval, relay an approval result, or report progress using the runtime’s expected data formats.
Why use it?
It prevents agents from guessing, rewriting, or confusing security-related data. That avoids approvals failing or being linked to the wrong request.

Skill for Claude Code

Written for Claude Code: PreToolUse hook event.

Part of the gaia plugin — 38 skills, 9 agents, 11 hooks shipped together

Good fit Use it when an agent must request approval, relay an approval result, or report progress using the runtime’s expected data formats.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/metraton/gaia/agent-approval-protocol
Install

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.

Any agent
npx skills add metraton/gaia --skill agent-approval-protocol
Clone the repo
git clone --depth 1 https://github.com/metraton/gaia

Made for: Claude Code.

Or install gaia, the plugin that ships this one along with the rest of its 38 skills, 9 agents, 11 hooks.

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 agent-approval-protocol

README.md
[![agentmods](https://agentmods.dev/badge/skills/metraton/gaia/agent-approval-protocol.svg)](https://agentmods.dev/skills/metraton/gaia/agent-approval-protocol)
Your own site
<a href="https://agentmods.dev/skills/metraton/gaia/agent-approval-protocol"><img src="https://agentmods.dev/badge/skills/metraton/gaia/agent-approval-protocol.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,063 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 $0.00022 $0.01063
Opus 5 $0.00011 $0.00531
Sonnet 5 $0.00004 $0.00213
Haiku 4.5 $0.00002 $0.00106

Measured 7d ago against content hash d91fcbabc53d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

agent-approval-protocol 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 7d 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.

skills/agent-approval-protocol/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Approval Protocol

This is the approval data reference. Producer, presenter, and executor workflows live in their branch skills. Never author or derive security data that the runtime returns.

Identity and placement

  • Contract agent_id: ^a[0-9a-f]{16,}$.
  • Approval id: three spellings circulate and only one resolves. The canonical P- plus 32 lowercase hexadecimal characters is the fully-qualified id the runtime seals, and the only form to relay. A BARE 32 hex with no P- is what a refusal surface emits (NONCE_APPROVAL_PATTERN, APPROVE:<32 hex> in approval_constants.py). P- plus the FIRST 8 hex is what the CLI displays for readability (nonce[:8]) -- a label, never an address. Relay the canonical form exactly as received; agents never mint one, never pad a displayed truncation back to full length, and never reconstruct one from a prefix.
  • If the validator rejects the relayed id, that is a runtime seam, not your error. Do not re-spell it, do not retry variants, and above all never invent an id that merely looks resolvable -- a plausible 32-hex string is indistinguishable from a real one at the point it is read, so inventing one turns a visible seam into a silent false grant. Close NEEDS_VERIFICATION with the id verbatim in verbatim_outputs and name the rejection in open_gaps, so the seam is routed to whoever owns it instead of being absorbed as a failure of yours.
  • All consent data belongs inside top-level approval_request, not beside it or duplicated in evidence_report.
  • The fenced contract remains compatibility output; the DB is the durable source for lookup and reconciliation.

Single command

The runtime-sealed request carries operation, verbatim exact_content, scope, risk_level, rollback_hint, and rationale. The contract maps rollback_hint to rollback and adds the verification method and returned approval_id.

Plan-first COMMAND_SET

gaia approvals request-set accepts one or more ordered exact T3 commands -- including a single command requested proactively, before any attempt reaches PreToolUse. Its approval_request carries:

Read the full file on GitHub · 99 lines

Files

What ships with it

1 file 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.

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. 7d ago First seen · 99 lines · 22 tokens per session scan A d91fcbabc53d

Subscribe to this mod's changes

agent-approval-protocol is a skill published in the GitHub repository metraton/gaia (3 stars, last pushed 3d ago), licensed MIT. It adds 22 tokens to every session and 1,063 once invoked, about $0.0001 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