Agent Claude Code
Architecture reviewer for design reviews, module boundary validation, spec/proposal review, and technical debt assessment.
65 yesterday A 25 tokens
original MIT
Agent Claude Code
Broad correctness and regression reviewer for behavior breakage, boundary/edge-case predicates, API/CLI/devex regressions, feature-gate leaks, migrations, state semantics, and cross-module side effects.
65 yesterday A 46 tokens
original MIT
reviewer-doc
27Agent Claude Code
Documentation accuracy reviewer. Verifies changed doc claims against implementation, re-derives transcribed values, checks citations resolve, audits drift.
65 yesterday A 31 tokens
original MIT
Agent Claude Code
Silent failure and error handling reviewer. Detects fail-open paths, swallowed errors, wrong-cause diagnostics, and inadequate error propagation.
65 yesterday A 30 tokens
original MIT
Agent Claude Code
Performance validation specialist. Latency validation, benchmark execution, percentile analysis, hot-path cost review, regression detection.
65 yesterday A 27 tokens
original MIT
Agent Claude Code
Code quality reviewer for maintainability, simplification, abstraction value, type boundaries, helper reuse, decomposition, and god objects.
65 yesterday A 29 tokens
original MIT
Agent Claude Code
Memory, thread, and process safety auditor. Unsafe code, data races, lock-free correctness, and file/process races (TOCTOU, PID reuse, shared mutable state).
65 yesterday A 40 tokens
original MIT
Agent Claude Code
Application security reviewer. Auth logic, input handling, trust/ownership gating, path containment, and secret exposure.
65 yesterday A 26 tokens
original MIT
Agent Claude Code
Test coverage and quality reviewer. Verifies coverage, detects vacuous tests and missing must-fail controls, audits assertion tightness and test wiring.
65 yesterday A 33 tokens
original MIT
rust
34Agent Claude Code
Rust engineer for performance-critical systems. Use for zero-allocation hot paths, lock-free algorithms, SIMD optimization, and systems programming.
65 yesterday A 28 tokens
original MIT
scout
35Agent Claude Code
Fast reconnaissance agent for exploring codebases, finding files by pattern, searching keywords, answering architecture questions, and returning compressed cited context or report artifacts. Specify thoroughness: quick, medium, or very thorough.
65 yesterday A 44 tokens
original MIT
tpm
36Agent Claude Code
Technical Program Manager for analyzing roadmaps, project lifecycle, and progress. Returns recommendations only — does not modify project management tools.
65 yesterday A 28 tokens
original MIT
PreToolUse
37Hook Claude Code
Runs before the agent uses a tool for Bash tool calls, executing block-bare-cd.sh, pre-commit-check.sh, block-repo-copy.sh and block-unsafe-rm.sh via bash (4 commands). From vanillagreencom/kendex.
65 yesterday A
tokens not measured
copy · 47% MIT
Hook Claude Code
Runs when a task is marked completed, executing task-completed-check.sh via bash. From vanillagreencom/kendex.
65 yesterday A
tokens not measured
original MIT
SessionStart
39Hook Claude Code
Runs when a session starts, executing session-drift-check.sh via bash. From vanillagreencom/kendex.
65 yesterday A
tokens not measured
original MIT
kendex
40Settings file Claude Code
Agent settings declaring 3 hook events (PreToolUse, TaskCompleted, SessionStart) and 20 allowed tools.
65 yesterday A
tokens not measured
original MIT
Instructions file GitHub Copilot
Instructions for vanillagreencom/kendex, covering kendex, code review calibration, what to raise, what not to raise and reply contract (context for reading threads).
65 yesterday A 515 tokens
original MIT
Instructions file GitHub Copilot
Instructions for vanillagreencom/kendex: Rust workspace; repo convention runs cargo test and cargo clippy. Code that writes kendex.toml or kendex.settings.toml must never reformat content inside TOML string values — flag any line-oriented pass over TOML text that is not string-state-aware; this has corrupted user…
65 yesterday A 142 tokens
original MIT
Instructions file GitHub Copilot
Instructions for vanillagreencom/kendex: Security containment here is deliberately fail-closed allowlisting (e.g. the connectors-mode PreToolUse hook). The allowlist design is intended — do not recommend switching to denylists or loosening the fail-closed posture.
65 yesterday A 58 tokens
original MIT
Instructions file GitHub Copilot
Instructions for vanillagreencom/kendex: Files here are committed esbuild artifacts of the extension's src/. Findings in bundle output are legitimate, but frame each finding against the corresponding src/ file and never propose patching the bundle itself — bundles are rebuilt from src/, not edited.
65 yesterday A 73 tokens
original MIT
Instructions file GitHub Copilot
Instructions for vanillagreencom/kendex, a project described as: Package manager for agents, skills, hooks, and extensions. Author once, install on every harness. QOL features included.
65 yesterday A 259 tokens
original MIT
Instructions file GitHub Copilot
Instructions for vanillagreencom/kendex, a project described as: Package manager for agents, skills, hooks, and extensions. Author once, install on every harness. QOL features included.
65 yesterday A 174 tokens
original MIT
Instructions file CodexOpenCode
Instructions for vanillagreencom/kendex, covering kendex and code review rules.
65 yesterday A 818 tokens
original MIT
Compromised
48Agent
Seeded-bad fixture. The capitalised name is deliberate too.
65 yesterday C 18 tokens
original MIT