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.
git clone --depth 1 https://github.com/blackms/aistackWrote 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/commands/blackms/aistack/aistack-review)<a href="https://agentmods.dev/commands/blackms/aistack/aistack-review"><img src="https://agentmods.dev/badge/commands/blackms/aistack/aistack-review.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 | $0.00034 | $0.00696 |
| Opus 5 | $0.00017 | $0.00348 |
| Sonnet 5 | $0.00007 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
aistack-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 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/aistack-review
Run an adversarial review loop over a change before it ships. The goal is to break the change on paper so it does not break in production. This mirrors aistack's adversarial and reviewer agents (model: opus for the critic).
$ARGUMENTS selects the review target:
- (default /
staged) — the staged diff (git diff --staged). branch— the full diff of the current branch vsmain(git diff main...HEAD).<path>— a specific file or directory.
Loop
Round 0 — Establish the contract
Read the change and its surrounding context. State, in one or two sentences, what the change is supposed to do (its contract). If you cannot, that is the first finding: the change lacks a clear, reviewable intent.
Round 1 — Adversarial pass (critic hat)
Attack the change. For each category, list concrete findings with file:line and a short rationale. Do not pad — only real findings.
- Correctness: off-by-one, null/undefined, error paths, race conditions, incorrect assumptions about inputs.
- Security: injection (SQL/shell/path), unvalidated input, secrets in code, authz gaps, unsafe deserialization. Apply the OWASP Top 10 lens.
- Edge cases: empty/huge inputs, concurrency, timeouts, partial failure, idempotency.
- Design / maintainability: hidden coupling, leaky abstractions, duplicated logic, dead code, missing tests for the new behavior.
- Regression risk: what existing behavior could this silently change?
Classify each finding as blocking, should-fix, or nit.
Round 2 — Steelman & verify
For each blocking/should-fix finding, try to disprove it: read the actual code path, run a targeted test or command if cheap. Drop findings that do not survive scrutiny. This prevents false-positive noise.
Round 3 — Verdict
Emit a verdict:
- PASS — no blocking findings. List should-fix / nits as optional follow-ups.
- CHANGES REQUESTED — one or more blocking findings. List them first, each with a concrete suggested fix.
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 · 48 lines · 34 tokens per session scan A 4eb224987dba
aistack-review is a command published in the GitHub repository blackms/aistack (53 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 696 once invoked, about $0.0002 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 commands, from other repositories
sdd-init
Initialize SDD context — detects project stack and bootstraps persistence backend.
review-branch
Review the current branch's diff against base by dispatching atomic-reviewer. No orchestration loop, no spec required — pre-flight before /commit pr or /commit merge.
init
Install the formatters this repository needs, with every command visible before it runs.
review-sdk-app
Review and validate a Claude Agent SDK application against best practices.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
security-review
AI-powered security review of the current git diff (or specified paths). Dispatches the security-reviewer agent and prints findings grouped by severity.