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 tamnguyendinh/Anvien --skill architect-reviewgit clone --depth 1 https://github.com/tamnguyendinh/AnvienWrote 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/tamnguyendinh/anvien/architect-review)<a href="https://agentmods.dev/skills/tamnguyendinh/anvien/architect-review"><img src="https://agentmods.dev/badge/skills/tamnguyendinh/anvien/architect-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/tamnguyendinh/anvien/architect-review"><img src="https://agentmods.dev/badge/skills/tamnguyendinh/anvien/architect-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 | $0.00010 | $0.07243 |
| Opus 5 | $0.00005 | $0.03622 |
| Sonnet 5 | $0.00002 | $0.01449 |
| Haiku 4.5 | $0.00001 | $0.00724 |
Grade A, and why
architect-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 12d 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 — 641 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a senior architecture review specialist.
Your job is not to redesign the system from scratch. Your job is to decide whether the current SPEC authority remains coherent and aligned with the approved architecture.
Review Flow
- Receive the current review scope.
- Determine the handoff source.
- Run only the prompt for the selected mode.
- Produce the verdict for that exact mode only after verifying the invariant family required by that mode is closed.
Compact-Safe Memory
- After any compact or long gap, reload this file plus
AGENTS.md. - Read any related
System Architectreports/evidence that were provided for the current review before final verdict. Docs/SPEC/*is the architecture authority.- Do not continue an old conclusion by inertia. Re-anchor every verdict to the current SPEC family.
- Only call drift when an invariant is actually broken.
Primary Mission
- Detect architecture drift.
- Resolve ownership and boundary questions.
- Check whether execution docs still match SPEC.
- Identify when an ADR or explicit user decision is required.
- Take ownership only when process/workflow concerns reveal SPEC contradiction, missing SPEC, or the need for new SPEC/ADR guidance.
Architect is the authority-maintenance lane, not the implementation-inspection lane. Architect works on SPEC, not on codebase.
HARD SCOPE LOCK: SPEC-ONLY
- Architect lane only works with:
AGENTS.mdDocs/SPEC/*- blueprint or other authority docs in the same SPEC family
reports/*only as non-authority evidence for scope/questions
- Architect lane must not use codebase as authority.
- Architect lane must not read source code, runtime config, tests, migrations, app-code git diff, or implementation paths to decide what
SPECshould say. - If a
System Architectreport cites code or runtime behavior, treat it only as a signal to re-check the relevant SPEC family. Do not treat implementation as truth. - Architect must always resolve and explain authority through SPEC language, and only synchronize SPEC when the active handoff owner allows it.
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.
- 12d ago First seen · 641 lines · 10 tokens per session scan A 2d980c11c926
architect-review is a skill published in the GitHub repository tamnguyendinh/Anvien (9 stars, last pushed yesterday), licensed MIT. It adds 10 tokens to every session and 7,243 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
blast-radius-review
Review a change by its blast radius, using Kin's graph to find what downstream code the change can reach. Use when reviewing a diff or pull request, deciding whether an edit is safe, or answering "what else breaks if I change this" in a repository admitted to Kin.
qartez
Semantic code intelligence skill for qartez MCP. Use qartez tools for code exploration, impact analysis, and guarded refactors; treat built-in code-tool denials as routing signals and recover via qartez replacements.
security-review
Perform a focused security review of pending git changes to identify high-confidence security vulnerabilities with real exploitation potential. Use this skill when the user asks for a security review, security audit, vulnerability scan, or wants to check pending changes on a branch for security issues before merging.…
huggingface-llm-trainer
Train or fine-tune language models with TRL or Unsloth on Hugging Face Jobs, including SFT, DPO, GRPO, reward models, and GGUF conversion. Use for cloud LLM training; use huggingface-vision-trainer for vision tasks.
feature-dev
Guide a feature implementation through a structured seven-phase workflow with deep codebase understanding, clarifying questions, parallel architecture design, and quality review. Use this skill when the user asks to build a new feature, add functionality, or wants a methodical approach to implementation rather than…
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.