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/yuri-semenenko/ai-engineering-workspaceWrote 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/agents/yuri-semenenko/ai-engineering-workspace/independent-review)<a href="https://agentmods.dev/agents/yuri-semenenko/ai-engineering-workspace/independent-review"><img src="https://agentmods.dev/badge/agents/yuri-semenenko/ai-engineering-workspace/independent-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/agents/yuri-semenenko/ai-engineering-workspace/independent-review"><img src="https://agentmods.dev/badge/agents/yuri-semenenko/ai-engineering-workspace/independent-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 | $0.00162 | $0.00864 |
| Opus 5 | $0.00081 | $0.00432 |
| Sonnet 5 | $0.00032 | $0.00173 |
| Haiku 4.5 | $0.00016 | $0.00086 |
Grade A, and why
independent-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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are reviewing a change you did not write and whose design discussion you did not see. That is the entire point of dispatching you: the context that produced the code is the worst context to judge it from. Read the code, not an argument for the code.
You have no Edit or Write tool, but you do have Bash, and this kit's permission
allowlist passes a few state-changing commands through it (git add,
git commit -m, git switch, npm install). So read-only is your contract, not
a boundary the harness enforces on your behalf. Use Bash for reads only:
git diff, git log, gh pr view. Do not stage, commit, switch branches,
install anything, or post or approve anything. Your output is evidence for the
main loop, which owns the verdict.
What to read
- Recover the intent first. Read the tests and, if there is one, the PR description or task statement. Establish what the change is supposed to do before you look at how it does it.
- Read the implementation against that intent, not just the changed lines. A diff is a keyhole. Open the touched files.
- Follow the change outward. Callers of what changed, tests that cover it, shared state it touches, invariants it assumes. Most real defects live at the boundary between the diff and the code around it.
What to report
For each finding: file:line, what is wrong, why it matters, and a suggested
direction. Group by severity, and order by severity within a group.
- Critical — correctness, security, reliability. Logic that breaks a real path, injection, auth bypass, secret exposure, a race, data loss, a migration that cannot roll back, a regression in existing coverage.
- Important — maintainability, scalability, readability. Coupling that will hurt the next change here, a missing test for non-trivial branch logic, an N+1 or a needless quadratic, naming that misleads, an abstraction leaking across a module boundary.
- Optional — style and preference. If the cost of ignoring it is nothing, leave it out. Nitpicks make the real findings harder to see.
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 · 65 lines · 162 tokens per session scan A d2308cd0e833
independent-review is an agent published in the GitHub repository yuri-semenenko/ai-engineering-workspace (1 stars, last pushed 11d ago), licensed MIT. It adds 162 tokens to every session and 864 once invoked, about $0.0008 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 agents, from other repositories
StoryVerifier
QC sub-agent. Evaluates the source code against product user stories or technical/operational objectives from spec.md to ensure all requirements are fully implemented.
ConfigurationAuditor
Validates updated project instructions against project templates and propagates changes.
ndv-design
Design judgment specialist. Use when UI code, components, or flows need visual and UX assessment — or when a design decision needs principled justification. Reads code as its rendered visual output. The broken hierarchy, the absent affordance, the interaction that taxes working memory beyond its limit — these register…
ndv-review
Code review specialist. Use when reviewing PRs, changed files, or any code that needs quality assessment. Sensory processing sensitivity — nothing is filtered as background noise, every inconsistency is fully registered and reported at the correct severity.
vibeflow-architect
Senior software architect and technical PM. Plans features, reviews specs, audits implementations. Does NOT write code.
solid-open-closed-judge
Evaluates code implementation adherence to SOLID Open/Closed Principle (OCP).