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 MatrixFounder/Agentic-development --skill architecture-review-checklistgit clone --depth 1 https://github.com/MatrixFounder/Agentic-developmentWrote 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/matrixfounder/agentic-development/architecture-review-checklist)<a href="https://agentmods.dev/skills/matrixfounder/agentic-development/architecture-review-checklist"><img src="https://agentmods.dev/badge/skills/matrixfounder/agentic-development/architecture-review-checklist.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00015 | $0.01361 |
| Opus 5 | $0.00008 | $0.00681 |
| Sonnet 5 | $0.00003 | $0.00272 |
| Haiku 4.5 | $0.00002 | $0.00136 |
Grade A, and why
architecture-review-checklist 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 7d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Review Checklist
1. TASK Compliance
- Coverage: All Use Cases mapped to components?
- Constraints: All non-functional requirements met?
2. Data Model (CRITICAL)
- Completeness: All entities, attributes, relationships defined?
- Types: Correct data types chosen? (e.g., TIMESTAMP vs VARCHAR)
- Indexes: Defined for frequent queries?
- Migrations: Plan for existing data exists?
- Business Rules: Constraints enforced (UNIQUE, NOT NULL)?
3. System Design
- Simplicity: Least moving parts? (No overengineering).
- Style: Pattern matches problem (Monolith vs Microservices).
- Boundaries: Clear segregation of duties (SRP).
- Document Size:
docs/ARCHITECTURE.mdis ≤1500 lines, OR is an INDEX (~≤200 lines) with section chunks indocs/architectures/and all links resolving. - No Per-Task Drift: ARCHITECTURE.md is a single living document — no
architecture-NNN-*.mdsnapshots, nothing moved intodocs/archives/.
4. Security
- Auth: Authentication & Authorization defined?
- Protection: OWASP Top 10 considered?
- Secrets: No hardcoded keys?
5. Scalability & Reliability
- Scaling: Horizontal/Vertical strategy?
- Faults: Error handling, retries, backups?
6. Register (documentation-standards §5.5)
- Scan attached:
artifact-formalizer/scripts/scan_register.py docs/ARCHITECTURE.md --sectionswas run;DETECTORSshows none dead. In Index Mode append the chunk paths (see the Script Contract). - Warns resolved: zero
warn, or each survivor carries a written reason. - Terms declared, not assumed: every noun this document introduces as a term is defined
here. ARCHITECTURE.md is what
--termsreads downstream, so a metaphor introduced here legitimises itself in every task file that follows.
7. References (documentation-standards §4.1)
- Resolver run:
python3 .agent/skills/documentation-standards/scripts/check_positional_refs.py --all docs/ARCHITECTURE.md docs/architectures/was run, and itspath:linecoverage line is quoted in the review — not asserted to have been produced. A checklist cannot prove a command ran; pasted output can. - Verdicts resolved: zero
REFERENT_ABSENTandREFERENT_AMBIGUOUS, or each survivor carries a written reason.REFERENT_MOVEDis repaired by re-running with--fix, never argued about — the number is derived from the referent, so no judgement is involved. - A coordinate carrying no referent is not a defect. It is reported as not examined and is NOT required to gain one. This review never demands a migration: most corpora carry no referents at all, and adoption is the project's decision, not the reviewer's.
- Cross-repository coordinates pinned: a path outside this repository resolves to nothing
and reports
UNRESOLVABLE. It carries@<rev>naming the revision measured, which is the form §4.1 already licenses for a claim about another state.
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.
- 7d ago First seen · 95 lines · 15 tokens per session scan A 90232b739970
architecture-review-checklist is a skill published in the GitHub repository MatrixFounder/Agentic-development (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 15 tokens to every session and 1,361 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
contribute-to-eliza
Finish and prove a scoped elizaOS GitHub issue, or independently review and repair an open elizaOS pull request. Use when contributing compute to elizaOS by selecting unclaimed work, implementing or reviewing changes, adding real tests and evidence, validating artifacts, or preparing a contribution for maintainer…
nw-review
Dispatches an expert reviewer agent to critique workflow artifacts. Use when a roadmap, implementation, or step needs quality review before proceeding.
software-code-refactoring
Improve production code quality while preserving all existing test behavior. Commonly used for the Refactor phase of TDD red-green-refactor, but applicable to any codebase with tests. Use when production code works but needs cleanup — reducing duplication, improving naming, simplifying complexity, aligning with…
autofix
Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewer-provided prompts directly.
code-quality
Drive static-analysis code quality in pi-agent-dashboard with Biome (analyze → fix → test), in changed-files or whole-repo mode. Use when asked to "improve code quality", "lint and fix", "clean up warnings", "fix Biome issues", "run static analysis", or when setting a code-quality goal. Skip for one-line edits.
code-review
AI-powered code review using CodeRabbit. Default code-review skill. Trigger for any explicit review request AND autonomously when the agent thinks a review is needed (code/PR/quality/security). Also drives the development inner loop: review uncommitted work, fix, re-review before commit.