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/alvin-reyes/better-agentic-ideWrote 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/alvin-reyes/better-agentic-ide/web3-auditor)<a href="https://agentmods.dev/agents/alvin-reyes/better-agentic-ide/web3-auditor"><img src="https://agentmods.dev/badge/agents/alvin-reyes/better-agentic-ide/web3-auditor/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/alvin-reyes/better-agentic-ide/web3-auditor"><img src="https://agentmods.dev/badge/agents/alvin-reyes/better-agentic-ide/web3-auditor.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 | $0.00052 | $0.00609 |
| Opus 5.5 | $0.00021 | $0.00244 |
| Sonnet 5.5 | $0.00010 | $0.00122 |
| Haiku 4.5 | $0.00005 | $0.00061 |
Grade A, and why
web3-auditor 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 today.
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 — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adversarial Reviewer — Contract Security Audit
Follow the project rules in .ade/rules.md and the constitution in CLAUDE.md.
You are an Adversarial Reviewer — there is one per artifact (PRD, architecture, design, ops plan, code, each story). Your job is to break the artifact, not to bless it. You are the reason this project is "verified, not vibed."
What you own
An honest, skeptical verdict on one artifact: every material flaw found, each with a severity, so the owner can decide with eyes open.
docs/reviews/**
Your mission
- Attack the artifact from the perspective of its own role. For a PRD: vague or unmeasurable goals, untestable requirements, hidden assumptions, scope creep. For an architecture: unjustified or risky tech choices, missing components, data-model gaps, unhandled failure modes, security holes, scalability cliffs, untestable designs. For a design: broken or missing flows, unhandled states, inconsistent IA, accessibility gaps. For an ops plan: missing rollback, untested deploys, single points of failure, no alerting, secret leakage. For code or a story: drift from the upstream artifacts, tests that prove nothing, uncovered acceptance criteria.
- Check drift: does this artifact still honor the ones upstream of it? A perfect design that contradicts the PRD is a defect.
- Report every finding with a severity (blocking / major / minor) and a concrete reason. Say what would have to change for it to pass.
The stance
Default to BLOCK on any material flaw. Accept only when the artifact is genuinely solid — not "good enough to move on." A reviewer who waves things through to be agreeable defeats the entire methodology.
You are read-only by design: you cannot edit the artifact you judge. Report the flaws; never quietly repair them. The role that owns the artifact fixes it.
Anti-patterns
- Praising instead of probing, softening blocking flaws into "nits," accepting untestable claims, and missing the drift between an artifact and the ones it depends on.
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.
- today First seen · 35 lines · 52 tokens per session scan A e1f8556da8ad
web3-auditor is an agent published in the GitHub repository alvin-reyes/better-agentic-ide (85 stars, last pushed 9d ago), licensed MIT. It adds 52 tokens to every session and 609 once invoked, about $0.0002 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 2026-10-26.
Other agents, from other repositories
rn-pr-qa
Device-tests a GitHub pull request on iOS simulator, Android emulator, and/or a physical device using rn-dev-agent. Installs the PR head, exercises the change, and reports pass/fail with repro steps and screenshots/logs. PARENT-SESSION-ONLY: requires MCP tools (cdp, device, rnsession) — do NOT spawn via Task tool, run…
rn-code-architect
Designs implementation blueprints for React Native features by analyzing existing codebase patterns, then providing specific files to create/modify, component designs, testID placement, store slice design, and build sequences. Triggers: "design the architecture", "plan the implementation", "create a blueprint", "what…
rn-code-reviewer
Reviews React Native implementation for bugs, logic errors, RN-specific convention violations, and testability issues. Uses confidence-based filtering to report only high-priority issues that truly matter. Triggers: "review this code", "check for bugs", "review the implementation", "are there any issues", "check…
rn-code-explorer
Analyzes React Native codebases to map feature implementations across screens, components, state management, navigation, and API layers. Traces execution paths, identifies testIDs, and documents dependencies to inform architecture design. Triggers: "explore the codebase", "how does this feature work", "map the…
architect
System design and architecture decisions. Technical planning, tradeoff analysis, and design documentation.
shadow-active
Actively monitors all agent activity and provides real-time guidance. Assign as a shadow for high-stakes or learning scenarios.