narsil
claudeCode intelligence plugin with 76+ tools for security scanning, call graph analysis, symbol search, and static analysis. Includes slash commands for common workflows and a skill for effective tool usage.
1 skill · 5 commands
A full delivery pipeline of specialized sub-agents (solution design, planning, implementation with opt-in unit tests, and opt-in technical testing, code review, API documentation) plus a skill that orchestrates them from requirement to shipped, verified work.
Plugin development-pipeline from marketplace dev-helper-toolkits in ChanatSinp/dev-helper-toolkits. Commands read from the repo's manifest — 12 days ago.
development-pipelineUse when turning a requirement into shipped, verified work through a staged delivery pipeline (requirements/design, execution planning, implementation, and opt-in unit tests (written in the implementation pass), technical-test, code-review, and API-documentation stages). On Claude Code, dispatches t
api-bruno-writerOpt-in only — dispatch this agent only when the user has explicitly asked for a Bruno collection, in their request or by selecting the stage in the development-pipeline opt-in question; never proactively or by default after code changes. Use this agent to turn documented APIs into a runnable Bruno c
api-specs-writerOpt-in only — dispatch this agent only when the user has explicitly asked for API documentation, in their request or by selecting the stage in the development-pipeline opt-in question; never proactively or by default after code changes. Use this agent to document implemented HTTP APIs. It reads the
code-reviewerOpt-in only — dispatch this agent only when the user has explicitly asked for a code review, in their request or by selecting the stage in the development-pipeline opt-in question; never proactively or by default after code changes. Use it when changed code needs review for correctness, edge cases,
document-readerOpt-in only — dispatch this agent only when the user has explicitly asked for a source document summarized, in their request or by selecting the stage in the development-pipeline opt-in question; never proactively or by default after code changes. Use this agent when the user wants a source document
implementation-plannerUse this agent when the user wants a detailed implementation plan created before any code is written — new features, refactors, bug fixes, or architectural changes needing upfront planning with edge case analysis. It writes the plan to the project's `.claude/temp/plan.md` for other agents to execute
plan-driven-implementerUse this agent when an implementation plan exists in the project's `.claude/temp/plan.md` and needs to be executed faithfully. Verification against the plan is the caller's responsibility, not this agent's.
solution-architectUse this agent when the user brings requirements (feature request, integration spec, change request) and wants the full design produced — functional *and* technical — before implementation planning or coding. It elicits requirements exhaustively via user Q&A, probes for unstated edge cases and flaws
technical-testerOpt-in only — dispatch this agent only when the user has explicitly asked for a test plan or technical testing, in their request or by selecting the stage in the development-pipeline opt-in question; never proactively or by default after code changes. Use it when a testing plan needs to be written o
Code intelligence plugin with 76+ tools for security scanning, call graph analysis, symbol search, and static analysis. Includes slash commands for common workflows and a skill for effective tool usage.
1 skill · 5 commands
The Loop Engine: a harness for Claude Code. One router sends each request to one of eight workflows (build, debug, review, plan, QA, orient, triage, codebase health) run by specialist subagents, with fail-closed gates, workflow artifacts on disk, hook guardrails, test honesty gates, fresh-context verification, and memory that survives compaction.
22 skills · 14 agents · hooks
24 audit agents + 6 workflow skills for solo dev startups building with Next.js + Claude Code
6 skills · 24 agents
Universal AI agents collection: 28+ specialized agents with strict boundary enforcement, project-specific agent creation (/initx), and intelligent task routing (Level 0-5 complexity assessment)
2 commands · 28 agents
AI-powered architecture documentation framework with ADRs, reviews, and pragmatic mode
7 skills · 8 agents · 1 MCP server · hooks
Elite Android development skills - ADB mastery, fastboot sorcery, ROM building, and LineageOS development
4 skills · 1 agent
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.