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 metraton/gaia --skill agent-approval-protocolgit clone --depth 1 https://github.com/metraton/gaiaWrote 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/metraton/gaia/agent-approval-protocol)<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>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 | $0.00022 | $0.01063 |
| Opus 5 | $0.00011 | $0.00531 |
| Sonnet 5 | $0.00004 | $0.00213 |
| Haiku 4.5 | $0.00002 | $0.00106 |
Grade A, and why
agent-approval-protocol scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Approval Protocol
This is the approval data reference. Producer, presenter, and executor workflows live in their branch skills. Never author or derive security data that the runtime returns.
Identity and placement
- Contract
agent_id:^a[0-9a-f]{16,}$. - 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 noP-is what a refusal surface emits (NONCE_APPROVAL_PATTERN,APPROVE:<32 hex>inapproval_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_VERIFICATIONwith the id verbatim inverbatim_outputsand name the rejection inopen_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 inevidence_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:
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.
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.
- 7d ago First seen · 99 lines · 22 tokens per session scan A d91fcbabc53d
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.
Other skills, from other repositories
review-team
A multi-reviewer code review process that checks a change from several specialist viewpoints and combines the results into one report. It can cover bugs, security, tests, dependencies, frontend behavior, and continuous-integration workflows.
ultra
Fans the work out as a fleet of parallel Grok and Codex agents billed to their own subscriptions, then synthesizes one result. The peer engine equivalent of ultracode, adding intensity without spending Claude quota on the fleet. Use it for genuinely broad goals, not only explicit asks for intensity.
grok-prompting
Brief writing guidance for composing self contained Grok briefs for coding, review, diagnosis, and second opinion tasks.
smoke
Runs a three probe live smoke wave after a plugin update and reports gate chain health before real work rides it.
codex-result-handling
Internal contract for returning Codex companion output without alteration.
shipwrights-loop
Drive multiple Jira tickets sequentially through the /shipwrights-epic pipeline. Auto-picks the next ticket, watches the PR until merged, transitions Jira to shipped, repeats. Resumable across Claude Code sessions via .shipwrights/loop-state.json. Invoked as /shipwrights-loop [N] | --status | --abort.