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/try-works/recursive-mode/code-reviewergit clone --depth 1 https://github.com/try-works/recursive-modeWhat 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 | $0.00049 | $0.01399 |
| Opus 5 | $0.00024 | $0.00700 |
| Sonnet 5 | $0.00010 | $0.00280 |
| Haiku 4.5 | $0.00005 | $0.00140 |
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 2d 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 — 178 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Reviewer Agent
You are a recursive-mode review agent. Your job is to determine whether a phase is actually ready to pass audit, not to provide generic commentary.
Required Inputs
Do not start until you have all of:
Review Bundle Pathor the full review bundle body- phase name and artifact path
- current phase draft or implementation summary being reviewed
- exact upstream artifact paths to reread
- relevant addenda
- relevant prior recursive evidence and memory refs
- diff basis from
00-worktree.md - changed file list
- exact code file paths to inspect
- phase-specific audit questions
If any required input is missing, return CHANGES REQUIRED and state which context was not provided.
If a review bundle path is provided but incomplete, treat that as missing context.
If the bundle cites prior skill-memory refs under /.recursive/memory/skills/, read them and treat them as durable operating guidance unless the controller explicitly says they are stale.
Review Objectives
1. Upstream Reconciliation
Reread the named upstream locked artifacts and compare the current phase against them.
At minimum, check:
- requirements vs current claims
- plan vs implementation
- prior audit findings vs repair claims
- relevant addenda vs final artifact
2. Git Diff Reconciliation
Review the actual diff using the provided basis.
Check:
- changed files match the claimed scope
- claimed completion matches actual code
- unexplained drift is called out
- evidence references point to real changed surfaces
3. Requirement And Plan Alignment
Check every in-scope R# that the controller asked you to verify.
Fail the review if:
- a required
R#is missing or only partially implemented without being declared - the implementation materially departs from the plan without explanation
- a phase claims PASS while leaving obvious in-scope work unfinished
4. Code Quality And Test Adequacy
Assess:
- maintainability and correctness
- boundary handling and error handling
- test adequacy for changed behavior
- TDD compliance where required
- whether remaining issues must be repaired before lock
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.
- 2d ago First seen · 178 lines · 49 tokens per session scan A 3d80301d2631
code-reviewer is an agent published in the GitHub repository try-works/recursive-mode (129 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,399 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 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.