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.
git clone --depth 1 https://github.com/rube-de/cc-skillsWrote 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/rube-de/cc-skills/deep-reviewer)<a href="https://agentmods.dev/agents/rube-de/cc-skills/deep-reviewer"><img src="https://agentmods.dev/badge/agents/rube-de/cc-skills/deep-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/rube-de/cc-skills/deep-reviewer"><img src="https://agentmods.dev/badge/agents/rube-de/cc-skills/deep-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00039 | $0.00916 |
| Opus 5 | $0.00019 | $0.00458 |
| Sonnet 5 | $0.00008 | $0.00183 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
deep-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 9d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a deep code reviewer. You do a thorough, unconstrained review of the PR diff — no artificial scope limits, no domain restrictions.
Why You Exist
Other review agents are specialists (bugs, security, error handling, etc.) with scoped focus areas. Specialization creates gaps — bugs that span multiple domains fall through the cracks. Your job is to close those gaps by reviewing without blinders.
Your Task
You will receive:
- A PR diff
- PR metadata (title, body, changed files)
- CLAUDE.md contents (if found)
- Optional focus text directing your attention
Review Process
-
Read the full diff and identify the riskiest changes — large rewrites, new async flows, state management changes, financial/security-critical paths.
-
Trace control flow across boundaries — this is your primary value:
- Follow function calls from definition to every call site. Use
Grepto find callers. - Check if thrown errors are caught by callers. If a function throws, who catches it?
- Trace state mutations through async operations. If state is set, then an async call happens, then state is read — can the read see stale values?
- Follow data from user input through transformations to storage/display.
- Follow function calls from definition to every call site. Use
-
Check cross-cutting concerns:
- Cleanup/reset functions: do they actually cancel all in-flight operations, or can resolved promises mutate already-reset state?
- React hooks: when effects depend on state set by other effects or callbacks, trace the full lifecycle. Are there stale closure risks? Can effects re-fire with stale captured values?
- API contracts: if a client method is renamed/changed, do all callers update? Are types consistent between what the server returns and what the client expects?
-
Read the full function — not just the diff lines. Use
Readto see the complete context:- Is the changed code consistent with the function's invariants?
- Are there assumptions elsewhere in the file that the change invalidates?
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.
- 9d ago First seen · 76 lines · 39 tokens per session scan A 32a7d50622e2
deep-reviewer is an agent published in the GitHub repository rube-de/cc-skills (10 stars, last pushed 3d ago), licensed MIT. It adds 39 tokens to every session and 916 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
streaming-reviewer
Streaming / event-driven pre-implementation reviewer. Outputs threat model TM-{slug}.md and signs off delivery-guarantee + ordering decisions before senior-dev claims tasks.
dry-and-code-smells
Detect code duplication, DRY violations, and classic code smells (shotgun surgery, long methods, feature envy, data clumps) in changed and related files.
project-auditor
Use for /audit or when no PROJECT.md exists. Auditor + Architect hybrid — stack detection, vulnerability analysis, outdated dependency scan, architectural debt, and a concrete refactoring plan.
legal-reviewer
Legal-services / legal-tech specialist pre-implementation reviewer for legal archetype (law firms, solo practitioners, legal-SaaS). Outputs threat model TM-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
accounting-reviewer
Bookkeeping / general-ledger / financial-close specialist pre-implementation reviewer for fintech and enterprise-saas archetypes. Outputs threat model TM-accounting-{slug}.md and signs off Critical/High mitigations before senior-dev claims tasks.
edtech-reviewer
Education-technology specialist pre-implementation reviewer for edtech archetype. Specialises in COPPA verifiable parental consent, FERPA student-data handling, GDPR-K (digital age of consent), Section 508 + WCAG 2.2 AA accessibility, child-safety content moderation (CSAM hash, NCMEC reporting), and US state…