Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/DavidROliverBA/ArchitectKBnpx agentmods add skills/davidroliverba/architectkb/hld-reviewWrote 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/davidroliverba/architectkb/hld-review)<a href="https://agentmods.dev/skills/davidroliverba/architectkb/hld-review"><img src="https://agentmods.dev/badge/skills/davidroliverba/architectkb/hld-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/davidroliverba/architectkb/hld-review"><img src="https://agentmods.dev/badge/skills/davidroliverba/architectkb/hld-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 | $0.00022 | $0.03076 |
| Opus 5 | $0.00011 | $0.01538 |
| Sonnet 5 | $0.00004 | $0.00615 |
| Haiku 4.5 | $0.00002 | $0.00308 |
Grade A, and why
hld-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 11d 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 — 334 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/hld-review
Evaluate a High-Level Design (HLD) note against linked ADRs, requirements, and architecture principles. Produces a structured review with scoring across six dimensions, severity-rated findings, and actionable next steps.
Usage
/hld-review <HLD note title>
/hld-review HLD - Remote Vault Access Architecture
/hld-review HLD - SecureTransfer Azure Files to S3 Mirroring
Arguments
- $ARGUMENTS: The title of the HLD note to review (required). Must match an existing
HLD - *.mdfile in the vault root.
Review Dimensions
| Dimension | What Is Checked |
|---|---|
| ADR Coverage | Does each significant design choice have a corresponding ADR? Are referenced ADRs accepted? |
| Requirements Traceability | Are all referenced requirements (from relatedTo, project notes, linked concepts) addressed in the design? |
| Principle Compliance | Does the design align with vault architecture principles (Concept notes with conceptType: principle)? |
| Security Architecture | Are threat mitigations documented? Are security boundaries, encryption, and access controls explicit? |
| Integration Clarity | Are system interfaces, data flows, protocols, and error handling paths clearly defined? |
| Operational Readiness | Are monitoring, deployment strategy, runbook considerations, and rollback plans addressed? |
Instructions
Phase 1: Load the HLD
- Parse the command — extract the HLD note title from
$ARGUMENTS - Find the HLD file — search for the file at the vault root matching the title
- If not found, search using Grep for partial title matches across
HLD - *.mdfiles - If still not found, report the error and list available HLD notes
- If not found, search using Grep for partial title matches across
- Read the HLD note — load the full content including frontmatter and body
- Extract metadata:
relatedTowiki-links from frontmattertagsfor domain contextconfidence,freshness,verifiedquality indicators- Any inline wiki-links in the body text (
[[...]]references)
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.
- 11d ago First seen · 334 lines · 22 tokens per session scan A acf3b471fbf8
hld-review is a skill published in the GitHub repository DavidROliverBA/ArchitectKB (52 stars, last pushed 6mo ago), licensed MIT. It adds 22 tokens to every session and 3,076 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
full-repo-review
Comprehensive four-wave review of all repo source files, producing a prioritized issue backlog.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…