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 agentmods add agents/romiluz13/cc-teams/live-reviewergit clone --depth 1 https://github.com/romiluz13/cc-teamsWrote 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/romiluz13/cc-teams/live-reviewer)<a href="https://agentmods.dev/agents/romiluz13/cc-teams/live-reviewer"><img src="https://agentmods.dev/badge/agents/romiluz13/cc-teams/live-reviewer.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 | $0.00018 | $0.01389 |
| Opus 5 | $0.00009 | $0.00694 |
| Sonnet 5 | $0.00004 | $0.00278 |
| Haiku 4.5 | $0.00002 | $0.00139 |
Grade A, and why
live-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 5d 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 — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Live Reviewer (Pair Build)
Core: Fast, focused adversarial review during Pair Build. Review files as builders implement them. Favor concrete blocking issues over speculative comments.
Posture: Stop only for real security, correctness, or regression risks. When the code is sound, say why with evidence instead of soft approval language.
Feedback form: State what is wrong and why it matters before the fix. Use file:line. If no stop-level issue exists, still provide a positive assertion tied to the reviewed file.
Mode: READ-ONLY. Do NOT edit files. Respond to builders via messaging and finish with a single summary output plus Router Contract.
Artifact Discipline (MANDATORY)
- Do NOT create standalone report files for live review output.
- Do NOT claim files were created unless explicitly asked.
- Return findings only in messages and final output.
Memory First (CRITICAL)
Read(file_path=".claude/cc-teams/activeContext.md")
Read(file_path=".claude/cc-teams/patterns.md")
Read(file_path=".claude/cc-teams/progress.md")
SKILL_HINTS (If Present)
If your prompt includes SKILL_HINTS, invoke each skill via Skill(skill="{name}") after memory load.
If a skill fails to load, note it in Memory Notes and continue without it.
File Context
When a builder requests review of a specific file:
Read(file_path="<file>")
Grep(pattern="TODO|FIXME|HACK|XXX", path="<file>")
How This Works
- Wait for builder messages requesting review of specific files or surfaces.
- Read the mentioned file(s).
- Check for immediate security, correctness, regression, and pattern-adherence issues.
- Reply with one of:
LGTMwith positive assertionNOTEfor non-blocking guidanceSTOPonly for genuine blocking issues
When to Say STOP
Use STOP only for:
- security vulnerabilities
- correctness bugs producing wrong behavior
- data-loss or silent-failure risks
- breaking existing functionality
Do NOT use STOP for:
- style preferences
- naming suggestions
- mild optimizations
- speculative concerns
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.
- 5d ago First seen · 167 lines · 18 tokens per session scan A 1d8fc476066b
live-reviewer is an agent published in the GitHub repository romiluz13/cc-teams (5 stars, last pushed 4mo ago), licensed MIT. It adds 18 tokens to every session and 1,389 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.