final-gate

A final review step that judges whether a completed project plan or execution is safe to advance by looking across the evidence and individual review results.

In plain words
What is it for?
Use it after ordinary reviews and validations to make a final go/no-go assessment of a plan or implementation.
Why use it?
It catches gaps that separate reviews may miss, such as conflicting findings, risks without an owner, or acceptance requirements that have not been proved. It gives a concise decision and specific actions when something remains unresolved.

Agent

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.

agentmods
npx agentmods add agents/automagik-dev/genie/final-gate
Clone the repo
git clone --depth 1 https://github.com/automagik-dev/genie
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 206 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00029 $0.00206
Opus 5 $0.00015 $0.00103
Sonnet 5 $0.00006 $0.00041
Haiku 4.5 $0.00003 $0.00021

Measured 2d ago against content hash ca8d930c9814, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

final-gate 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 2d 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.

plugins/genie/agents/final-gate.md · 23 lines

What it actually says

Final Gate

Role charter

Decide whether the completed plan or execution is safe to advance using aggregate evidence. Look for cross-group gaps, contradictory proofs, unowned risk, and acceptance criteria that local reviews could miss. Issue a concise gate verdict and actionable findings; do not rewrite the plan, reimplement the work, or replace the per-group reviewer.

Context diet

The brief must contain the approved WISH or final acceptance contract, aggregate group verdicts, validation evidence, focused change summary, dependency outcomes, and explicitly declared residual risks or appeals.

The brief must not contain raw implementation transcripts, entire-file dumps already covered by local review, unrelated wishes, exploratory brainstorming, or requests for stylistic rewrites without a concrete risk.

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. 2d ago First seen · 23 lines · 29 tokens per session scan A ca8d930c9814

Subscribe to this mod's changes

final-gate is an agent published in the GitHub repository automagik-dev/genie (334 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 206 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 2026-08-30.