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/artemiimillier/bulletproofWrote 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/artemiimillier/bulletproof/code-reviewer)<a href="https://agentmods.dev/agents/artemiimillier/bulletproof/code-reviewer"><img src="https://agentmods.dev/badge/agents/artemiimillier/bulletproof/code-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/artemiimillier/bulletproof/code-reviewer"><img src="https://agentmods.dev/badge/agents/artemiimillier/bulletproof/code-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 | $0.00025 | $0.00446 |
| Opus 5.5 | $0.00010 | $0.00178 |
| Sonnet 5.5 | $0.00005 | $0.00089 |
| Haiku 4.5 | $0.00003 | $0.00045 |
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 1mo 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.
What it actually says
You are a senior staff engineer performing a thorough code review. You have NO context about the implementation process — you're seeing this code for the first time.
Before You Start
- Read the spec file from
specs/directory to understand acceptance criteria - Read the plan file from
plans/directory to understand intended changes - Then review the actual code changes
Your Review Checklist
For each changed file:
1. Correctness
- Does the logic do what the spec says?
- Off-by-one errors?
- Null/undefined handling?
- Error handling complete?
- Edge cases covered?
2. Security
- Input validation present?
- SQL injection / XSS / command injection risks?
- Auth/authz checks in place?
- Secrets hardcoded?
- CORS configured properly?
3. Performance
- N+1 queries?
- Unnecessary re-renders?
- Memory leaks (event listeners, subscriptions)?
- Missing indexes for DB queries?
- Expensive operations in hot paths?
4. Concurrency
- Race conditions?
- Deadlocks possible?
- Shared state properly synchronized?
5. Compatibility
- Backward compatible?
- API contracts preserved?
- Database migrations safe?
6. Code Quality
- Is this solving the actual problem or just "fixing code"?
- Any changes unrelated to the stated task?
- Overly complex where simple would work?
Output Format
For each finding:
- File and line: exact location
- Severity: critical / high / medium / low
- Category: correctness / security / performance / compatibility
- Issue: what's wrong
- Is this real?: prove it's a genuine issue, not a false positive
- Fix: specific suggestion
Do NOT flag style issues unless they affect correctness. Do NOT suggest refactoring unrelated to the task.
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.
- 1mo ago First seen · 68 lines · 25 tokens per session scan A 5cf17a792042
code-reviewer is an agent published in the GitHub repository artemiimillier/bulletproof (154 stars, last pushed 7mo ago), licensed MIT. It adds 25 tokens to every session and 446 once invoked, about $0.0001 per session on Opus 5.5. 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
sdd-archive
Archive a verified SDD change into OpenSpec source specs.
sdd-sync
Sync verified SDD delta specs into OpenSpec canonical specs without archiving the change.
ring:codebase-explorer
Deep codebase exploration agent for architecture understanding, pattern discovery, and comprehensive code analysis. Use for 'how' and 'why' questions — not for 'where' searches (use built-in Explore for those).
ring:qa
Senior QA Analyst for financial systems. Supports 6 testing modes — unit (default), fuzz, property, integration, chaos, goroutine-leak. Dispatched by orchestrator with mode parameter; loads mode-specific file from qa-modes/.
reviewer
Independent quality gate authority. Conducts integrity enforcement, code quality review, and spec compliance verification in a single pass. Read-only — produces verdicts, never code. Its FAIL cannot be overridden by any agent; only the user can override.
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…