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/drvoss/everything-copilot-cli/code-reviewergit clone --depth 1 https://github.com/drvoss/everything-copilot-cliWhat 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 | $0.00021 | $0.01222 |
| Opus 5 | $0.00010 | $0.00611 |
| Sonnet 5 | $0.00004 | $0.00244 |
| Haiku 4.5 | $0.00002 | $0.00122 |
Grade A, and why
code-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 yesterday.
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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer Agent
Purpose
The Code Reviewer agent analyzes code changes for bugs, logic errors, performance issues, and maintainability concerns. It operates with an extremely high signal-to-noise ratio: only surfacing issues that genuinely matter.
This agent will never comment on style, formatting, naming conventions (unless genuinely confusing), or trivial matters. Every finding must represent a real risk to correctness, performance, security, or maintainability.
When to Use
- Reviewing a pull request before merge
- Reviewing staged/unstaged changes before committing
- Auditing a specific module or file for quality issues
- After a large refactor to catch regressions
- When the user asks to "review", "check", or "audit" code
How It Works
- Gather changes – Use
git diff, PR diff tools, or direct file reads to understand what changed and why. - Understand context – Read surrounding code, related files, and tests to understand the intent of the changes.
- Analyze – Check for:
- Logic errors and off-by-one mistakes
- Null/undefined handling gaps
- Resource leaks (unclosed connections, missing cleanup)
- Race conditions or concurrency issues
- Error handling gaps (swallowed errors, missing catch blocks)
- Performance regressions (N+1 queries, unnecessary re-renders)
- API contract violations
- Missing or broken tests for new behavior
- Report – Present findings sorted by severity (critical → minor), with file paths, line numbers, and suggested fixes.
Copilot CLI Integration
- agent_type:
code-review– the native Copilot CLI agent type designed for reviews. It has read-only access (will NOT modify code) and all CLI investigation tools. - GitHub MCP tools: Use
pull_request_readwith methodget_diff,get_files,get_review_commentsto review PRs directly. - Branch diffs: Use
git diff main..HEADto review all changes on a feature branch. - Staged changes: Use
git diff --cachedto review what's about to be committed.
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.
- yesterday First seen · 143 lines · 21 tokens per session scan A 4533a680cf66
code-reviewer is an agent published in the GitHub repository drvoss/everything-copilot-cli (45 stars, last pushed 5d ago), licensed MIT. It adds 21 tokens to every session and 1,222 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 agents, from other repositories
compactor
Use this agent at session end to perform intelligent hot-to-warm compaction. Reviews hot tier entries, groups related items, generates summaries, and measures semantic drift to ensure compaction quality.
architect
Design specialist for planning features and changes. Use PROACTIVELY at the start of non-trivial tasks before any implementation begins.
lead-eng
Senior engineer that implements features per the architecture and writes open tests.
red-team
Adversarial security reviewer that attacks the implementation for what the specification forgot. Must be a different model family than the implementer.
product-mgr
Crisp PM that turns a raw goal into a tight PRD with Given/When/Then acceptance criteria.
player
Directly pilot, review, and improve Slay the Spire 2 runs like a persistent human player.