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 orchestrator-present-approvalgit 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/orchestrator-present-approval)<a href="https://agentmods.dev/skills/metraton/gaia/orchestrator-present-approval"><img src="https://agentmods.dev/badge/skills/metraton/gaia/orchestrator-present-approval/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/metraton/gaia/orchestrator-present-approval"><img src="https://agentmods.dev/badge/skills/metraton/gaia/orchestrator-present-approval.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00019 | $0.02091 |
| Opus 5 | $0.00010 | $0.01045 |
| Sonnet 5 | $0.00004 | $0.00418 |
| Haiku 4.5 | $0.00002 | $0.00209 |
Grade A, and why
orchestrator-present-approval 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 today.
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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Present Approval — Orchestrator Branch
Present trusted contract data exactly. Do not execute, derive, shorten, reorder, or silently expand it.
The surface is rendered, never composed
WHAT the user sees is produced Gaia-side from the sealed payload by one
function -- hooks/adapters/consent_presentation.py::render_native_text, over
that module's VISIBLE_FIELDS table -- and it comes out identical on every
host. Its exact shape, field set, render order and absence semantics are stated
in template.md. Show that text verbatim. Compose nothing, summarise nothing,
reorder nothing, translate no label.
For an existing pending id, read both presentation pieces with gaia approvals show <approval_id> --consent-surface. The JSON visible_text field is that
rendered surface byte-for-byte; print it unchanged. Use the JSON
approve_label field unchanged for the approval control -- Gaia sources it from
render_approve_label, so the presenter must not rebuild it. This read records
no SHOWN event and makes no decision or grant.
Present the surface as text, then ask a minimal decision
A presentation is two pieces. Print the rendered surface verbatim as console
text -- the MESSAGE. Then ask a binary decision -- the QUESTION -- carrying one
line of operation, the command count, and the approval id, and nothing else.
template.md states both shapes literally, together with the four rules that
make the split safe: the id on both ends, adjacency with a reprint duty, the
minimum the question carries, and a binary control set with no always.
That order is deliberate and the reason is narrow. When the surface travels
inside a host's decision payload, whether the host's renderer displays every
line of it is unverifiable from outside that host: nothing you can read back
confirms the user saw the ROLLBACK line, or the eighth command's fingerprint,
or anything past a truncation the renderer applied silently. Consent over a
truncated surface is exactly the failure this whole protocol exists to prevent,
and that exposure stands recorded as unmitigated -- closable only by real
end-to-end work against each host, never by a claim made here. Printed as
console text, completeness stops depending on a renderer nobody can inspect and
starts depending on the user's own terminal.
What ships with it
2 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.
- today Changed · +7 lines be57a091f603
- 10d ago First seen · 164 lines · 19 tokens per session scan A 73d5eb94b865
orchestrator-present-approval is a skill published in the GitHub repository metraton/gaia (3 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 2,091 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.