By brennacodes
Track filesystem changes in ~/.claude/ and other directories — git snapshots, changelog parsing, diff queries, and plugin dependency health checks
Parse and query changelogs — filter by version, change type, keyword, or show latest entries. Works with target changelogs and individual plugin CHANGELOGs.
Plugin health check — scans all installed plugins for path dependencies, cross-references with recent changes, classifies risk (HIGH/MEDIUM/LOW), and suggests fixes.
Capture a git snapshot of a tracked directory — detects changes, commits current state, updates snapshot log. Use to checkpoint before/after updates.
Show filesystem changes between snapshots — filter by time range, path pattern, or change type. Presents diffs at your preferred detail level.
Initialize claude-scout in .things/ - configure a tracking target, set up git snapshots, auto-detect changelogs, register collections. Required before other claude-scout skills.
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 composable, portable, interactive knowledge system that grows with you — 9 plugins for Claude Code with a shared data layer, cross-plugin coordination, and migration tooling.
| Plugin | What it does | Plugin-specific README |
|---|---|---|
| things | Schema-aware data layer for ~/.things/ — config, registry, search, sync, tag indexing | README |
| i-did-a-thing | Log professionally-relevant experiences, build a searchable evidence arsenal, generate tailored resumes | README |
| what-did-you-do | Practice interviews with persona-driven coaching, powered by your logged evidence | README |
| what-do-you-know | Deepen understanding through concept quizzing, gap analysis, and learning plans | README |
| mark-my-words | Write and publish blog posts across 7 static-site platforms — standalone or from your evidence logs | README |
| heres-the-thing | Persuasion and positioning engine — tailor any subject for any audience, in any medium, and track what works | README |
| think-like | Expert thinking profiles for code review, architecture, security, and debugging | README |
| screenshotr | Precise macOS screenshots with crop, resize, and format control | README |
| session-scout | Search, browse, and resume Claude Code sessions across all projects | README |
[!WARNING] Upgrading from v3? Version 4 introduced breaking changes to the config and data layout. Your data is safe, but you'll need to migrate. See Migrating from v3 for details.
Seven plugins share a single config and data layer at ~/.things/, powered by things. Log an experience once, then use that experience for knowledge reinforcement through what-do-you-know, interview prep and resume building through what-did-you-do, or persuasive positioning through heres-the-thing. Feed urls or reference material to mark-my-words and it creates a voice profile for you to use in blog posts. Feed those same urls or reference material to think-like and it creates expert-driven planning, reviews, and audits without re-telling the story. All git-tracked so you can take your things with you and never miss a beat.
screenshotr and session-scout are standalone utilities with no .things/ dependency.
Set up the foundation first with:
/things:setup-thing
Then configure each plugin's specialties with its own setup skill (e.g. /setup-idat, /setup-wdyd, /setup-htt, etc.).
| Log it | Practice it | Learn from it | Write about it | Make them care | Think like an expert |
|---|---|---|---|---|---|
/thing-i-did | /practice | /explore | /from-things | /pitch | /profile |
| evidence arsenal resume bullets interview talking points | coached feedback readiness scores gap identification | concept maps gap analysis learning plans | published post first-person story blog with metrics | strategy briefs tailored deliverables outcome tracking | code review architecture plans security analysis |
/plugin marketplace add brennacodes/brenna-plugs
/plugin install things@brenna-plugs
/plugin install i-did-a-thing@brenna-plugs
/plugin install what-did-you-do@brenna-plugs
/plugin install what-do-you-know@brenna-plugs
/plugin install mark-my-words@brenna-plugs
/plugin install heres-the-thing@brenna-plugs
/plugin install think-like@brenna-plugs
/plugin install screenshotr@brenna-plugs
/plugin install session-scout@brenna-plugs
The schema-aware data layer that powers the plugin ecosystem. Creates and manages ~/.things/ — config, registry, central tag index, and cross-machine sync. Domain-ignorant: it knows about collections, indexes, tags, and file structures — not what logs or resumes are. Run this setup first; every other .things/ plugin depends on it.
npx claudepluginhub brennacodes/brenna-plugs --plugin claude-scoutLog 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.
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/.
Apply expert thinking profiles to code reviews, architecture evaluation, and security audits -- think like DHH, Sandi Metz, or build your own expert profiles
Session workflow helpers - knowledge capture, confusion handling, course correction, clipboard copy
Persistent memory across sessions. Learns preferences, conventions, and corrections automatically.
Core skills: ecosystem guide, skill creator, research patterns, session reflection, and plugin development. Includes UserPromptSubmit hook for forced skill evaluation.
Local-first personal AI identity layer for MCP-compatible coding tools. Stores your lessons, decisions, playbooks, and project context as local JSON. AI proposes; high-risk items wait for your review, and everything stays visible and reversible. Local-first, no cloud, no account.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Frontend design skill for UI/UX implementation