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 markoblogo/abvx-agent-skills --skill architecture-deepening-reviewgit clone --depth 1 https://github.com/markoblogo/abvx-agent-skillsWrote 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/markoblogo/abvx-agent-skills/architecture-deepening-review)<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/architecture-deepening-review"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/architecture-deepening-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/markoblogo/abvx-agent-skills/architecture-deepening-review"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/architecture-deepening-review.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00064 | $0.00549 |
| Opus 5 | $0.00032 | $0.00275 |
| Sonnet 5 | $0.00013 | $0.00110 |
| Haiku 4.5 | $0.00006 | $0.00055 |
Grade A, and why
architecture-deepening-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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Deepening Review
Find refactors that increase leverage and locality. A deeper module hides meaningful behavior behind a smaller, clearer interface.
Vocabulary
- Module: code with an interface and implementation.
- Interface: everything callers must know, including types, invariants, errors, ordering, config, and side effects.
- Seam: place where behavior can vary without editing callers.
- Adapter: concrete implementation behind a seam.
- Depth: useful behavior hidden behind a small interface.
- Locality: related behavior and knowledge concentrated in one place.
Review Workflow
- Read the nearest README, architecture docs, domain glossary, ADRs, and tests when present.
- Map the user-facing or domain workflow before judging structure.
- Look for friction:
- understanding one concept requires bouncing across many files;
- modules pass through data with little leverage;
- tests exist only around extracted fragments, not real behavior;
- domain rules are duplicated across callers;
- adapters exist in theory but only one implementation exists;
- hidden coupling crosses package or component boundaries;
- naming does not match domain language.
- Apply the deletion test: if removing a module only moves complexity into callers, it may be shallow. If removing it spreads domain complexity everywhere, it is probably earning its keep.
- Rank candidates by payoff, risk, and confidence.
Candidate Format
For each candidate:
- files/modules;
- current friction;
- proposed deeper module or seam;
- expected locality and leverage gain;
- testability improvement;
- risks and migration path;
- recommendation strength: strong, worth exploring, or speculative.
Do not implement broad refactors without user confirmation. For implementation, carve one vertical slice and preserve behavior with tests.
Optional HTML Report
When the user asks for a shareable architecture review, executive-readable report, or visual artifact, do not inline a long prose dump. Route the findings into html-diagram-artifact or html-brief-artifact after the candidate list is stable. The HTML artifact should stay evidence-backed: files/modules, friction, proposed seam, benefit, risk, and first slice.
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 · 59 lines · 64 tokens per session scan A 67fec517370f
architecture-deepening-review is a skill published in the GitHub repository markoblogo/abvx-agent-skills (16 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 549 once invoked, about $0.0003 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
printing-press-output-review
Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode (substring-match relevance, format bugs, silent source drops, ranking failures). Invoked via the Skill tool by the main printing-press skill at Phase 4.85 and printing-press-polish…
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
issue-root-resolution
Trigger: root audit, atacar la raíz, issue roots, backlog roots, mechanism map, deletion-driven fix, resolver issues de raíz, close outdated issues. Audit and resolve issue clusters by verified root cause.
rdd-defect-workflow
Trigger: RDD, receipt-driven development, review authority, receipt/lineage, correction/recovery, delivery gate/kill switch, bounded review defects. Guide work.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
semgrep-rule-creator
Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns. Use when writing Semgrep rules or building custom static analysis detections.