What is phoenix-final-gate?

A final security review step for deciding whether a Phoenix feature specification is ready to ship. It checks required security evidence and blocks release when critical issues remain.

Use it to make a documented SHIP or NO-SHIP decision after the earlier specification steps, and to flag softer concerns such as missing metrics or regulatory details.

It prevents unclear requirements, missing proof, tenant-data exposure, weak authentication, and unsafe AI behaviour from reaching implementation.

phoenix-final-gate — Skill for Claude Code by Security-Phoenix-demo

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 Security-Phoenix-demo/security-skills-claude-code --skill phoenix-final-gate

Clone the repo

git clone --depth 1 https://github.com/Security-Phoenix-demo/security-skills-claude-code

Made for: Claude Code.

Or install phoenix-prd-pipeline, the plugin that ships this one along with the rest of its 13 skills.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/security-phoenix-demo/security-skills-claude-code/phoenix-final-gate/github.svg)](https://agentmods.dev/skills/security-phoenix-demo/security-skills-claude-code/phoenix-final-gate)

Your own site

<a href="https://agentmods.dev/skills/security-phoenix-demo/security-skills-claude-code/phoenix-final-gate"><img src="https://agentmods.dev/badge/skills/security-phoenix-demo/security-skills-claude-code/phoenix-final-gate/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/security-phoenix-demo/security-skills-claude-code/phoenix-final-gate"><img src="https://agentmods.dev/badge/skills/security-phoenix-demo/security-skills-claude-code/phoenix-final-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 198 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 951 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.

Model	Per session	Once invoked
Fable 5.1	$0.00198	$0.00951
Opus 5.5	$0.00079	$0.00380
Sonnet 5.5	$0.00040	$0.00190
Haiku 4.5	$0.00020	$0.00095

Measured 1mo ago against content hash 73460c7d2bc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

phoenix-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 1mo 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/phoenix-prd-pipeline/skills/phoenix-final-gate/SKILL.md · 105 lines

How it starts

The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Phoenix Security — Final Gate Reviewer (Role 10)

Token Budget: ≤800 tokens Depends On: All previous roles (01–09) Feeds Into: FEATURE_SPEC.md + Confluence push (if SHIP) Output: 10-final-gate.md

Hard Blockers (any = NO_SHIP)

Run this checklist explicitly — do not skip any item:

Critical ambiguities remaining (Role 05) > 0
Any MUST lacks proof path (Role 08, unverified_musts > 0 without downgrade rationale)
PSC-03 multi-tenancy not addressed in security requirements
PSC-06 auth layer not addressed for any new endpoint
PSC-08 AI agent autonomous action not gated (if LLM in scope)
Scope creep: requirements outside SCOPE_DEFINITION from Role 02
P0 security requirements NOT in Batch 1 (Role 09)
Active enterprise account requirements (Mimecast/JM/Anaplan) not covered at P0

Soft Warnings (flag, do not block)

Manual-only proof paths for non-security requirements
Missing success metrics vs Phoenix case study benchmarks
Batch count implies >4 weeks without CTO sign-off
Regulatory hooks not documented
Competitor brand names in user-facing copy

Output Schema

---
meta:
  role: 10-final-gate
  session_id: session-[YYYYMMDD-HHMMSS]
  token_count: [actual]
  decision: SHIP | NO_SHIP
  blocker_count: [N]
  status: complete
---

### FINAL_GATE

#### DECISION
SHIP | NO_SHIP

#### HARD_BLOCKER_CHECK
- PSC-03 multi-tenancy: addressed | missing
- PSC-06 auth: addressed | missing
- PSC-08 AI agent: addressed | N/A
- Critical ambiguities: [count]
- Unverified MUSTs: [count]
- Scope creep: detected | none
- P0 in Batch 1: yes | no
- Enterprise account coverage: complete | gaps → [list gaps]

#### BLOCKERS (max 10; NO_SHIP only)
- B1: <gap> → source role: 0N → fix required: <exact action>

#### NON_BLOCKING_IMPROVEMENTS (max 10)
- N1: ...

#### NEXT_ACTIONS (ordered; owner + ETA)
1. [@owner] <action> — <ETA>

Post-Gate Actions

On SHIP:

Save 10-final-gate.md
Compile FEATURE_SPEC.md (Phoenix PRD template)
Push to Confluence SPM space (Atlassian MCP — mandatory; fallback parent: 1273987073)
Ask once: "Want me to create Linear/Asana tickets, notify Slack, or email stakeholders?"
Status: ✅ Pipeline complete

Read the full file on GitHub · 105 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.

1mo ago First seen · 105 lines · 198 tokens per session scan A 73460c7d2bc8

Subscribe to this mod's changes

phoenix-final-gate is a skill published in the GitHub repository Security-Phoenix-demo/security-skills-claude-code (81 stars, last pushed 5d ago), licensed MIT. It adds 198 tokens to every session and 951 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-09-11.

Planning Security

phoenix-final-gate next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
phoenix-final-gateSecurity-Phoenix-demo/security-skills-claude-code	Skill	81	5d ago	MIT	A	198	Claude Code
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	yesterday	MIT	A	103	Claude Code