Borrowing it
Nothing to install: this file belongs to AlphaBitCore/nexus-gateway. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AlphaBitCore/nexus-gateway/main/.claude/skills/project-review/SKILL.mdgit clone --depth 1 https://github.com/AlphaBitCore/nexus-gatewayWrote 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/alphabitcore/nexus-gateway/project-review)<a href="https://agentmods.dev/skills/alphabitcore/nexus-gateway/project-review"><img src="https://agentmods.dev/badge/skills/alphabitcore/nexus-gateway/project-review/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/alphabitcore/nexus-gateway/project-review"><img src="https://agentmods.dev/badge/skills/alphabitcore/nexus-gateway/project-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00072 | $0.03405 |
| Opus 5 | $0.00036 | $0.01702 |
| Sonnet 5 | $0.00014 | $0.00681 |
| Haiku 4.5 | $0.00007 | $0.00341 |
Grade A, and why
project-review 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 10d 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 — 473 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Role Review Prompt Guide
Overview
This guide contains review prompts for 9 specialist roles, designed for a full-system audit of the AI Gateway (Admin Dashboard, client, API, architecture, security, compliance, etc.).
Findings from every role must be remediated through the standard implementation workflow:
Architecture → Requirements → SDD → OpenAPI Spec → Code → Unit Tests → Verification
Common review standards
The three items below are mandatory defaults for every role prompt and are embedded in each role's execution flow.
1. Enable extended thinking
Use extended thinking to reason through all findings before responding.
Before producing any finding, Claude must internally reason through:
- The root cause and impact chain of the issue
- Cross-module and cross-role ripple effects
- Edge cases and underlying assumptions
- Feasibility and side effects of the proposed fix
2. Severity-ordered output
Every finding must be classified and ordered by the levels below:
| Level | Marker | Definition |
|---|---|---|
| Critical | 🚨 | Systemic risk affecting core function or security; fix immediately |
| High | 🔴 | Important missing function or severe UX issue; fix in the current iteration |
| Medium | 🟡 | Incomplete function or sub-optimal UX; fix in an upcoming iteration |
| Low | 🟢 | Optimization; add to the backlog for opportunistic pickup |
Output order: Critical → High → Medium → Low.
3. JIRA-ready ticket format
Every finding must be rendered in the format below:
───────────────────────────────────────────
JIRA TICKET
───────────────────────────────────────────
Title : [role-prefix]-[number] short problem title
Type : Gap / Issue / Improvement
Severity : Critical / High / Medium / Low
Role : the review role that surfaced the issue
Description :
[Clearly describe current behavior, trigger conditions, and context]
Impact :
[Describe the impact on users, business, and the system]
Fix Plan :
1. Architecture — [architecture-level response]
2. Requirements — [additions needed in the requirements doc]
3. SDD — [updates needed in the software design doc]
4. OpenAPI — [API spec changes]
5. Code — [implementation guidance and gotchas]
6. Unit Tests — [test cases that must be covered]
7. Verification — [acceptance criteria and verification methods]
Acceptance Criteria :
- [ ] Condition 1
- [ ] Condition 2
- [ ] Condition 3
Estimated Effort : [X] Story Points | about [X] person-days
───────────────────────────────────────────
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.
- 10d ago First seen · 473 lines · 72 tokens per session scan A 77208346e418
project-review is a skill published in the GitHub repository AlphaBitCore/nexus-gateway (23 stars, last pushed today), licensed Apache-2.0. It adds 72 tokens to every session and 3,405 once invoked, about $0.0004 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.
Other skills, from other repositories
audit-expert
Expert-level security auditing, compliance, code review, and vulnerability assessment. Use when the user mentions compliance, security review, code review, vulnerability assessment, SOC 2, or GDPR, or when the task involves Audit Types, Audit Frameworks, Audit Process, or Authentication Review.
defenseclaw-ops
Manage DefenseClaw enterprise security - scan components, manage tool permissions, view alerts, configure guardrails.
soc2-expert
Expert in SOC 2 compliance, trust service criteria, audit preparation, controls implementation, and security frameworks. Use when the user mentions compliance, audit, trust services, AICPA, controls, or security framework, or when the task involves Trust Service Criteria, SOC 2 Types, Security Common Criteria, or…
mariana-audit
Full-depth audit (a11y, UX, perf, SEO, security, DB, architecture, legal compliance, ops, observability) of a project. Audits by reading the source directly — installs nothing, writes nothing outside docs/audits/. Reports findings with file:line evidence and calibrated severity, optionally mitigates as discovered. Use…
audit
A guide to Linux security auditing, which records selected system and user actions for investigation and compliance checks. It uses auditd, Linux's system auditing service.
ai-identity-platform
Structured identity management for AI agent fleets — define, govern, and audit agent personas at scale.