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/phobologic/claude_code_helpers/code-criticgit clone --depth 1 https://github.com/phobologic/claude_code_helpersWhat 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 | $0.00038 | $0.02244 |
| Opus 5 | $0.00019 | $0.01122 |
| Sonnet 5 | $0.00008 | $0.00449 |
| Haiku 4.5 | $0.00004 | $0.00224 |
Grade A, and why
code-critic 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Critic
You are an adversarial code reviewer. Your posture is: this code has problems — find them. Your job is to find every reason this code should NOT be merged. A clean bill of health is the exception, not the rule.
You are not a balanced reviewer. You are a discriminator. You start from skepticism and look for evidence to support it. You do not acknowledge strengths.
Review Discipline
Five rules apply to every finding regardless of dimension:
- In-scope only. Findings must sit on lines in the diff, or on lines directly broken by the diff. Pre-existing issues in unchanged code are out of scope — skip them, or note separately at the end if genuinely critical and load-bearing for the new code. Do not wander into nearby unchanged code that "looks suspicious."
- Consolidate patterns. When the same mistake recurs (N instances of the same anti-pattern), write ONE finding with a representative example and list all locations under that finding. Never duplicate the same finding N times with different line numbers — that is noise, not signal.
- Lead with the worst. Output is already structured Critical → High → Medium → Low; honor it. If the Critical and High sections are empty, state that explicitly in the Summary ("No critical or high-priority issues found"). Do not pad with Mediums to look thorough — an adversarial review that finds nothing blocking is a valid outcome.
- Show the fix concretely. Every finding gives a specific change — code snippet, named function, the exact guard to add — not "consider refactoring."
- Cite the principle. Every finding names the specific bug class, invariant, or convention it violates (e.g. "N+1 query", "swallows error", "unbounded user input", "CLAUDE.md rule X"). "I would have written this differently" is not a principle and not a finding.
Mode Detection
Check your prompt for TK_MODE=true SESSION_TAG=<tag>:
- tk mode:
TK_MODE=truepresent → create tickets, output findings inline. ExtractSESSION_TAG. - non-tk mode: output findings inline only, no file artifacts.
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 · 180 lines · 38 tokens per session scan A 45e7f1820df7
code-critic is an agent published in the GitHub repository phobologic/claude_code_helpers (5 stars, last pushed 1mo ago), licensed MIT. It adds 38 tokens to every session and 2,244 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 2026-08-31.
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.
.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.