By brennacodes
Capture, browse, and consume agentic blindspots - default tendencies that produce bad outputs in specific contexts. Records live as markdown files with YAML frontmatter under ~/.blindspots/.
Use when the user asks to capture, record, save, log, or write down a blindspot, anti-pattern tendency, or default agentic behavior to ~/.blindspots/. Do not use when the user asks to list, search, update, or consume existing blindspots - those are separate skills.
Use when the user asks to initialize, set up, bootstrap, or create the blindspots store at ~/.blindspots/. Idempotent. Do not use when the user asks to capture, list, search, update, or consume blindspots - those are separate skills.
1. Run the script: ! node ${CLAUDE_SKILL_DIR}/scripts/list-blindspots.js $ARGUMENTS
Use when an agent wants the blindspots that apply to its current task, the diff it is reviewing, the plan it is drafting, or any other working context. Pass keywords describing that context. Do not use when the caller wants to browse or text-search the store (use list or search).
Use when the user asks to search, find, or look up blindspots by category, tag, applies_when substring, or free text. Do not use when the user asks for an unfiltered list (use list), to capture a new record, or to update an existing one.
Modifies files
Hook triggers on file write and edit operations
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A marketplace of utility plugins for Claude Code.
A whitelist-based permission system for Claude Code skills. Declare what a skill is allowed to do in its SKILL.md frontmatter; anything not whitelisted falls through to the normal permission flow. Includes a dangerous-command safety net (rm -rf /, git push --force main, curl | bash, etc.) and desktop notifications when human input is actually needed.
Capture and act on todos, reminders, and notes. Items live as markdown files with YAML frontmatter under ~/.notably/. Reminders can fire via SessionStart surfacing, scheduled remote agents, or local macOS notifications. Slash-only; no model auto-triggering.
Capture, browse, and consume agentic "blindspots" - default tendencies that produce bad outputs in specific contexts, absent intervention. Records live as markdown with YAML frontmatter under ~/.blindspots/. Includes an agent-facing /blindspots:relevant skill that takes keywords and returns full records whose tags or categories union-match, so a calling agent can self-check before acting.
Add this marketplace in Claude Code:
/plugin marketplace add brennacodes/utilitry
Then install a plugin:
/plugin install permitcrab@utilitry
/plugin install notably@utilitry
/plugin install blindspots@utilitry
utilitry/
├── .claude-plugin/marketplace.json
└── plugins/
├── permitcrab/
├── notably/
└── blindspots/
To test a plugin locally during development, you can use the following command:
claude --plugin-dir path/to/plugin/repo
npx claudepluginhub brennacodes/utilitry --plugin blindspotsLog professional experiences -- accomplishments, lessons, expertise, decisions, influence, and insights -- and build tailored resumes from your evidence arsenal
Capture and act on todos, reminders, and notes. Storage at ~/.notably/ as markdown files with YAML frontmatter. Reminders fire via SessionStart surfacing, scheduled remote agents, or macOS notifications. Slash-only invocation, no model auto-triggering.
Whitelist-based permission system for Claude Code skills. Declare what a skill is allowed to do in its SKILL.md frontmatter; anything not whitelisted falls through to the normal Claude Code permission flow. Includes a dangerous-command safety net and desktop notifications when human input is needed.
Orchestrate plans, workflows, implementation tracking, and reviews - import plans from Claude sessions, create XML-enhanced workflows, review implementations against plans, resume work, and track progress
Apply expert thinking profiles to code reviews, architecture evaluation, and security audits -- think like DHH, Sandi Metz, or build your own expert profiles
Permanent coding companion for Claude Code — survives any update. MCP-based terminal pet with ASCII art, stats, reactions, and personality.
Intelligent prompt optimization: injects the right context at the right moment so Claude lands a better first output. Clarifies vague prompts with research-based questions, plus targeted nudges for approach selection, plan readability, workflow routing, background execution, subagent routing, output readability, user-decision questions, and plan-mode assessment
Comprehensive skill pack with 66 specialized skills for full-stack developers: 12 language experts (Python, TypeScript, Go, Rust, C++, Swift, Kotlin, C#, PHP, Java, SQL, JavaScript), 10 backend frameworks, 6 frontend/mobile, plus infrastructure, DevOps, security, and testing. Features progressive disclosure architecture for 50% faster loading.
Harness-native ECC operator layer - 67 agents, 271 skills, 92 legacy command shims, reusable hooks, rules, selective install profiles, and production-ready workflows for Claude Code, Codex, OpenCode, Cursor, and related agent harnesses
Memory compression system for Claude Code - persist context across sessions
Feature development with code-architect/explorer/reviewer agents, CLAUDE.md audit and session learnings, and Agent Skills creation with eval benchmarking from Anthropic.