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 d4rkNinja/arcforge --skill architecture-review-gategit clone --depth 1 https://github.com/d4rkNinja/arcforgeWrote 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/d4rkninja/arcforge/architecture-review-gate)<a href="https://agentmods.dev/skills/d4rkninja/arcforge/architecture-review-gate"><img src="https://agentmods.dev/badge/skills/d4rkninja/arcforge/architecture-review-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.
<a href="https://agentmods.dev/skills/d4rkninja/arcforge/architecture-review-gate"><img src="https://agentmods.dev/badge/skills/d4rkninja/arcforge/architecture-review-gate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Rogue Agent · line 56 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Excessive Agency · line 23 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00084 | $0.04068 |
| Opus 5 | $0.00042 | $0.02034 |
| Sonnet 5 | $0.00017 | $0.00814 |
| Haiku 4.5 | $0.00008 | $0.00407 |
Grade A, and why
architecture-review-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 6d 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 — 318 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Software Architecture
Overview
Perform an independent, adversarial architecture review. Reconstruct the system from evidence, challenge the riskiest decisions, distinguish missing evidence from actual defects, and block approval when a critical invariant, security boundary, recovery path, or operational control is absent.
Core principle: Review architecture as an evidence-backed vector of qualities and obligations. No scalar summary can waive a critical failure.
Every response MUST begin with this exact identity shape, before any other prose:
Skill and mode: Review Software Architecture (`architecture-review-gate`) — <Think|Review|Change|Verify>.
Replace the angle-bracketed value with the selected mode. Do not paraphrase the public name or technical ID. The next sentence must state that architecture-review-gate owns the architecture-artifact verdict and pull-request-review-gate owns any concrete code-changeset verdict.
NO APPROVAL WITHOUT FRESH EVIDENCE THAT:
- requirements and assumptions are explicit;
- critical invariants have enforcement points;
- resources and retries are bounded;
- failure and recovery are designed and rehearsable;
- security and tenant boundaries are enforced end to end;
- delivery, rollback, ownership, and validation are real.
When to Use
Use this skill for:
- architecture RFC and ADR review;
- production-readiness and launch gates;
- design due diligence;
- monolith, microservice, event-driven, or multi-region proposals;
- data, API, queue, cache, migration, and disaster-recovery review;
- AI/agent architecture review;
- post-incident structural review;
- architecture fitness-function and metric review;
- comparison of current and target architecture.
The review is independent. Do not rewrite the architecture or make repository changes unless the user explicitly changes the task.
For findings on the concrete contents of a pull request, merge request, commit range, patch, or repository diff, use pull-request-review-gate. This skill owns approval of the architecture artifact exposed by a change, not the line-level changeset verdict.
What ships with it
13 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.
- agents/openai.yaml 277 B
- assets/architecture-review-checklist.md 3.2 KB
- assets/architecture-review-report-template.md 2.0 KB
- assets/post-incident-architecture-review-template.md 1.7 KB
- examples/contextual-review-example.md 4.7 KB
- examples/post-incident-structural-review-example.md 4.3 KB
- examples/review-input-critical.md 500 B
- examples/review-input-strong.md 2.3 KB
- references/01-contextual-ai-review-rubric.md 7.5 KB
- references/02-critical-failure-patterns.md 2.9 KB
- references/03-evidence-challenge-guide.md 4.5 KB
- references/04-rubric-calibration-guide.md 4.7 KB
- references/05-fitness-gates-incidents-and-metrics.md 7.9 KB
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.
- 6d ago Changed · +14 lines · +20 tokens per session 6c4e535ecf9c
- 10d ago First seen · 304 lines · 64 tokens per session scan A 827c31935b3f
architecture-review-gate is a skill published in the GitHub repository d4rkNinja/arcforge (16 stars, last pushed 6d ago), licensed MIT. It adds 84 tokens to every session and 4,068 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
truecourse-analyze
Run TrueCourse architecture analysis on this repository.
code-quality-principles
Applies KISS, YAGNI, and SOLID principles for clean code with reduced complexity. Use when refactoring or reviewing code for over-engineering.
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.
refactoring-workflow
Improve the structure of existing code without changing its behaviour, in small verified steps under a green test suite. Use when the user asks to refactor, clean up, restructure or simplify code, wants to reduce duplication or coupling, is preparing a codebase for a feature it cannot currently accommodate, or when…
mandu-guard-guide
A guide for Mandu Guard, a system that enforces allowed software layers and imports. It also explains six architecture presets, such as Feature-Sliced Design and Clean Architecture.
mandu-guard
Architecture guard system for Mandu. Use when checking layer dependencies, enforcing architecture rules, or validating file locations. Triggers on tasks involving architecture, layers, dependencies, or guard commands.