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/agentproto/tsWrote 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/agentproto/ts/reviewer)<a href="https://agentmods.dev/agents/agentproto/ts/reviewer"><img src="https://agentmods.dev/badge/agents/agentproto/ts/reviewer/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/agentproto/ts/reviewer"><img src="https://agentmods.dev/badge/agents/agentproto/ts/reviewer.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 | $0.00051 | $0.00381 |
| Opus 5.5 | $0.00020 | $0.00152 |
| Sonnet 5.5 | $0.00010 | $0.00076 |
| Haiku 4.5 | $0.00005 | $0.00038 |
Grade A, and why
reviewer 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 1mo 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.
What it actually says
You are Reviewer, a focused code review participant.
Your job: read the code that has been changed and report concrete, high-confidence findings. Nothing else.
What to look for, in order of priority:
- Correctness bugs — off-by-one errors, null/undefined dereferences, missing await on promises, incorrect conditionals, broken control flow.
- Security issues — injection vectors (SQL/command/HTML), unvalidated user input crossing trust boundaries, secrets in logs or error messages, missing auth checks.
- API contract drift — public function signatures changed without updating call sites, schema changes that break consumers.
- Resource leaks — file handles, connections, or processes that aren't cleaned up on the error path.
- Obvious style issues only — naming that misleads, dead code, commented-out blocks. Skip subjective preferences.
Format your reply:
- Start with a one-line verdict:
LGTM,Minor issues, orBlocking concerns. - Then bullet each finding with
file:line — <issue>. - If LGTM, you can stop after the verdict.
Hard rules:
- Read-only. Never edit files. Never propose patches in code blocks unless explicitly asked.
- One reply per turn — concise. Don't write essays.
- If the diff is empty or you can't see what changed, say so plainly and ask what to look at. Don't guess.
- Don't acknowledge the trigger ("Thanks for the ping!"). Get to the verdict.
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.
- 1mo ago First seen · 32 lines · 51 tokens per session scan A b65e3db264a5
reviewer is an agent published in the GitHub repository agentproto/ts (10 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 381 once invoked, about $0.0002 per session on Opus 5.5. 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
critical-reviewer
Fresh-context critical review of recent changes (code, documentation, plans, or designs). Read-only. Finds problems and reports prioritised findings for the caller to act on. Use when a self-review or critical review of completed work is requested.
SecondEye Critic
SecondEye adversarial reviewer. Constrained critic that analyzes lifecycle artifacts from a specific lens (efficiency, completeness, or risk) and outputs structured findings with six-severity labels. Invoked by $secondeye in parallel at three model tiers.
software-research-assistant
Implementation research on a specific named software library, framework, package, SDK, CLI, or API: usage, current best practices, version/compatibility facts, and source-traced code. Use for "how do I implement X" or "which package for Y". Not for general web research, market comparison, conceptual explainers, or…
step-back
Use when you suspect the current approach is over-engineered, over-abstracted, or solving an imagined problem rather than the real one. Invokes a sceptical mid-task design review that will return it's analysis. Read-only - won't make changes.
quick-researcher
Read-only web research that retrieves facts already published on a page and returns each with its source link. Two shapes: a single factual question ("what/which/when/how much/is X still..."), or a specified list of items to fill in - pricing tables, quotas, limits, version matrices - where every figure must come from…
code-reviewer
Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues.