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 skills/subhansh-dev/agent-maxxing/deep-code-reviewnpx skills add subhansh-dev/agent-maxxing --skill deep-code-reviewgit clone --depth 1 https://github.com/subhansh-dev/agent-maxxingWhat 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 | $0.00024 | $0.00921 |
| Opus 5 | $0.00012 | $0.00461 |
| Sonnet 5 | $0.00005 | $0.00184 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
deep-code-review 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 — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Code Review — 8-Angle Methodology
Extracted from Claude Code's bundled code-review skill. This is the most thorough code review methodology available.
Review for recall: catch every real bug a careful reviewer would catch in one sitting. Catching real bugs matters more than avoiding false positives.
Phase 0 — Gather the diff
Run git diff @{upstream}...HEAD (or git diff main...HEAD / git diff HEAD~1) to get the unified diff under review. If there are uncommitted changes, also run git diff HEAD and include working-tree changes.
Phase 1 — Find candidates (8 independent angles)
Each angle surfaces up to 6 candidate findings with file, line, summary, and failure_scenario.
Angle A — Line-by-line diff scan
Read every hunk in the diff, line by line. Then read the enclosing function for each hunk — bugs in unchanged lines of a touched function are in scope. For every line ask: what input, state, timing, or platform makes this line wrong? Look for:
- Inverted/wrong conditions
- Off-by-one errors
- Null/undefined dereference
- Missing
await - Falsy-zero checks
- Wrong-variable copy-paste
- Error swallowed in catch
- Unescaped regex metacharacters
Angle B — Removed-behavior auditor
For every line the diff DELETES or replaces, name the invariant or behavior it enforced, then search the new code for where that invariant is re-established. If you can't find it, that's a candidate: a removed guard, a dropped error path, a narrowed validation, a deleted test covering a real case.
Angle C — Cross-file tracer
For each function the diff changes, find its callers (Grep for the symbol) and check whether the change breaks any call site: a new precondition, a changed return shape, a new exception, a timing/ordering dependency. Also check callees: does a parallel change in the same PR make a call unsafe?
Angle D — Reuse check
Flag new code that re-implements something the codebase already has. Grep shared/utility modules and files adjacent to the change, and name the existing helper to call instead.
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 · 84 lines · 24 tokens per session scan A 008ea7610db4
deep-code-review is a skill published in the GitHub repository subhansh-dev/agent-maxxing (2 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 921 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 skills, from other repositories
terminal-capture
Automates terminal UI screenshot testing for CLI commands. Applies when reviewing PRs that affect CLI output, testing slash commands (/about, /context, /auth, /export), generating visual documentation, or when 'terminal screenshot', 'CLI test', 'visual test', or 'terminal-capture' is mentioned.
batch
Execute batch operations on multiple files in parallel. Automatically discovers files, splits into chunks, and processes with parallel worker agents. Use /batch followed by operation and file pattern.
fleet-manager
Use when managing, triaging, restarting, escalating, or summarizing Codewhale Pod runs and workers.
gh-assign-issues
Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.
mcp-builder
Design, build, configure, or debug Model Context Protocol servers for codewhale, including stdio and HTTP/SSE transports.
extension-creator
Create, scaffold, customize, validate, and locally test Qwen Code extensions. Use when the user wants a new Qwen Code extension, needs help choosing an extension template, wants to add QWEN.md context, commands, skills, agents, MCP servers, settings, hooks, channels, or LSP servers, or asks how to link and test an…