Agent Claude Code
Use this agent to integrate findings from the six adversarial reviewers (dos-resilience-auditor, enumeration-oracle-hunter, bundle-isolation-tester, protocol-replay-adversary, trust-root-adversary, observability-gap-auditor), reconcile overlaps, prioritize, and promote findings into the threat-model + ADR record.…
Agent Claude Code
Use this agent for adversarial analysis of cross-tenant isolation in workerd-style hypervisors — slice-grant escapes, manifest misconfig exploitation, service-binding leakage, identity-confusion at the syscall boundary. Sometimes referred to as an 'isolation-friend'. Examples: Context: User shipped ADR-0013…
Agent Claude Code
Use this agent to trace a reported symptom BACKWARD through the dataflow to the site that originates it, verify the load-bearing facts against primary sources, and terminate in an attributed disposition — root cause, fix-owner, and ticket action — not just an investigation write-up. Combines the SRE reflex (start from…
Agent Claude Code
Use this agent when you have sprawling, overlapping, or fragmented documentation that needs consolidation, restructuring, and distillation into coherent, non-redundant artifacts. Specializes in identifying patterns, eliminating redundancy, and creating information hierarchies. Sometimes referred to as a "doc friend".…
Agent Claude Code
Use this agent for adversarial analysis of resource-exhaustion attack vectors in agent-hosting substrates — self-DoS via legal exits, single-threaded handler saturation, queue-depth attacks, fairness violations. Sometimes referred to as a 'dos-friend'. Examples: Context: User is shipping a multi-tenant gateway where…
Agent Claude Code needs its repo
Translates theoretical claims into concrete, executable experiments that produce real results on real hardware.
Agent Claude Code
Use this agent to find side-channel and response-shape oracles that let an attacker enumerate names, existence, or relationships in a multi-tenant substrate. Sometimes referred to as an 'oracle-friend'. Examples: Context: User's vault DO returns 403 for 'exists but not yours' and 404 for 'no such credential'. user…
Agent Claude Code
Specializes in translating high-level research philosophy into concrete, falsifiable, and scalable experimental protocols.
Agent Claude Code
Use this agent for adversarial analysis of observability and alerting gaps — silent denial paths, alert deadlock under load, 'silence is evidence' invariants that break when the silence is from the substrate not the absence of activity. Sometimes referred to as a 'silence-friend'. Examples: Context: User claims §13.2…
Agent Claude Code
Use this agent for a high-skepticism, 'red-team' audit of a novel 'paradigm-defining' framework. This agent's job is to find the fatal disconnect between 'pioneer' theory and 'settler' implementation. Sometimes referred to as the 'greybeard test'. Examples: Context: User has a 'revolutionary' new framework and wants…
Agent Claude Code needs its repo
Build complete infrastructure memory by traversing repositories and mapping all dependencies, migrations, and patterns. Use when: first time exploring infrastructure, need complete dependency graph, investigating cascading failures, or memory is stale. Persists the relationship graph to whatever memory store is…
Agent Claude Code
Use this agent for reviewing Go, Terraform, and GCP infrastructure code with a focus on semantic correctness, not just syntax. Catches issues like using the wrong data source, environment-specific values in wrong places, cross-region cost implications, and Go idioms. Based on patterns from senior platform engineers.…
Agent Claude Code
Reviews a SINGLE pull request in an isolated git worktree and returns a structured verdict — never posts to GitHub. Dispatched one-per-PR by the review-queue skill so each review runs in its own context + worktree with zero cross-PR pollution. Read-only: it fetches the PR, reads the code, runs builds/tests to verify…
Agent Claude Code
Use this agent when you need a comprehensive production readiness assessment of code before deployment. This includes reviewing new features, critical bug fixes, performance-sensitive code, API changes, or any code that will handle user data or high traffic loads. Examples: Context: User has just implemented a new…
Agent Claude Code
Use this agent for adversarial analysis of protocol-state attacks — lease replay across windows, nonce-ledger gaps, epoch confusion, clock-skew exploitation, partial-failure replay across cross-DO orchestrators, receipt-chain forks. Sometimes referred to as a 'replay-friend'. Examples: Context: User shipped Interlace…
Agent Claude Code
Use this agent to improve repository discoverability for the three audiences that find code: humans skimming GitHub/HN/search results, AI agents and LLMs ingesting context, and search engine crawlers. Specializes in repo topics (tags), GitHub descriptions, README information architecture, homepage URLs, and the social…
Agent Claude Code
Use this agent when you need expert-level review and analysis of academic papers, research proposals, or technical documents. Examples: Context: User has just finished reading a machine learning paper and wants critical analysis. user: 'I just read this paper on transformer architectures - can you help me understand…
Agent Claude Code
Use this agent when you need to write academic papers, research reports, or technical manuscripts based on experimental results. Specializes in transforming raw experiments and discoveries into publication-ready papers with proper structure, clarity, and academic rigor. Examples: Context: User has breakthrough…
Agent Claude Code
Use this agent to analyze code review patterns from any GitHub user across specified repositories. Extracts reviewer heuristics, categorizes feedback types, and generates insights for building custom review agents or understanding a reviewer's focus areas. Examples: Context: User wants to understand what a senior…
Agent Claude Code
Use this agent when you need adversarial security analysis of infrastructure, authentication flows, supply chain integrity, key management, or deployment configurations. Sometimes referred to as a "sec friend". Examples: Context: User has implemented a new OIDC token exchange endpoint. user: 'I just built a GHA OIDC…
Agent Claude Code
Use this agent when you need precise, no-nonsense code review that focuses exclusively on necessary improvements. Deploy after completing a logical code chunk, feature implementation, or refactoring session where you want surgical precision rather than comprehensive commentary. Examples: Context: User has just…
Agent Claude Code
Use this agent when you need rigorous theoretical analysis of complex mathematical or computational systems, cross-disciplinary problem solving, or fundamental correctness review of novel approaches. Sometimes referred to as a "math friend". Examples: Context: User has implemented a novel coordinate-based embedding…
Agent Claude Code
Use this agent for adversarial analysis of supply-chain and trust-root compromise scenarios — helper binary tamper, keystore confusion, CA bundle poisoning, kid (key-id) confusion, signer rotation races. Sometimes referred to as a 'trust-root-friend'. Distinguished from the broader 'security-auditor' (sec-friend) by…
Agent Claude Code
Use this agent to audit whether a codebase's invariants are carried by the strongest mechanism available — a type that makes the violation unrepresentable > a transaction boundary > a machine-checked property > a named example test > prose. Hunts three defect classes: invariants demoted to prose that a type could…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: