claude

second-brain

Session manager for a markdown vault: hooks that deliver rules, today's daily, open todos, newest lessons and the project hub into every session and re-deliver them after compaction, drift checks on every prompt, session wrap and daily logs, a per-session ledger, ruling capture, per-object decision records, agenda and weekly review, vault scaffolding, and vault health (audit, grooming, canon size budgets).

0 on GitHubby Max Sheahanv1.7.0MITupdated 3 days agoproductivity
/

Plugin second-brain from marketplace sheahan-skills in maxsheahan/claude-skills. Commands read from the repo's manifest — 3 days ago.

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (15)

  • calendar-summary

    Daily snapshot of today's calendar events and sent email. Writes a sidecar markdown file at Daily/YYYY-MM-DD.calendar.md in the vault with Meetings and Log sections only. Needs a calendar connector and an email connector of your own (for example Google Calendar and Gmail MCP servers); works from Cow

  • canon-health

    Diagnostic audit of the always-loaded canon's size, rule count, growth, recurrence data, and retrieval reliability, judged against the instruction-following evidence (adherence degrades past ~150-200 discrete rules; count is the operative unit, not chars; omissions dominate). Produces a ranked verdi

  • canon-slim

    Budget keeper for the always-loaded canon files (Rules-of-Engagement.md, root CLAUDE.md, Tasks/todo.md; budgets declared in vault-audit.py CANON_BUDGETS). When a file trips its budget, build a displacement ledger (every rule tagged keep / displace-to-lessons / compress, with the lessons.md pointer v

  • daily-generator

    Backward-looking end-of-day log generator. Drafts Daily/YYYY-MM-DD.md in the vault from today's calendar events, today's sent email, and git/file activity across configured project folders. Pre-fills Focus / Log / Meetings / New-in-the-vault sections from a skeleton. Mechanical by default, no prose

  • handoff-audit

    Audit a session-to-session handoff document against the rules in this skill's CHECKLIST.md. Manual triggers: 'audit handoff', 'review handoff', 'audit this handoff', 'is this handoff thorough', 'check the handoff', 'handoff audit', 'handoff review'. Automatic chain: also fires as the required final

  • morning-agenda

    Forward-looking daily agenda for the vault's owner. Triggers on 'what's on the agenda', 'what's on deck', 'what's on deck today', 'morning agenda', 'what do I have today', 'agenda check', 'today's plan', 'what's coming up today'. Pulls today's calendar events (through a calendar connector of your ow

  • object-record

    Pull the decision record of ONE object in ANY project before it is edited (a file, feature, component, prompt, image asset or sprite): its git history with every prior version viewable, the hub rules, project memory and lessons that name it, and the owner's own words about it from the transcripts. T

  • ruling-capture

    Write the owner's ruling down the same turn they make it, in ANY project: verbatim and dated, into that project's hub Rules section and its project-memory current-rules file, and mark what it supersedes. Use the moment the user decides something about the product ('do it', 'kill it', 'they need to l

  • session-ledger

    Keep this session's ledger: the request, the requirements it accumulates, the decisions and their reasons, and what done means; check work against it at scope changes, phase transitions, after compaction, and before a commit, deploy or PR. Use at the start of substantive work ('build X', 'fix Y', 'd

  • session-wrap

    End-of-session housekeeping agent. Records the session's decisions and rationale, blockers, and next step; updates project todo, appends a daily vault entry, refreshes the project hub, updates project memory, logs lessons, and recommends the model for the next phase. Use when the user says "wrap ses

  • todo-groom

    Triage Tasks/todo.md back to forward-only: move completed blocks to Tasks/journal.md verbatim (mechanical tier, no ruling needed), collapse superseded status-line chains to the newest state (judgment tier, the owner rules on deletions), and surface stale items by age tier for keep/park/kill calls. T

  • vault-doctor

    Run the vault's deterministic health audit (vault-audit.py, 19 checks covering root files, routing coverage, the Obsidian layer, hub/board/root triangle, hub YAML, canon size and rule-count budgets, generated-artifact staleness, pipeline freshness, misfiled backups, _inbox aging, todo hygiene, stale

  • vault-groom

    Remediation executor for the vault's red metrics: repair dead wikilinks (walk-per-item), tie curated orphans into the graph (tie-orphans.py), backfill missing frontmatter on curated notes, normalize ../-prefixed wikilinks (normalize-wikilinks.py), file vault-root strays, and age out _inbox items. Th

  • vault-setup

    Scaffold a NEW, self-contained Obsidian vault from embedded templates: a real .obsidian/ config (core plugins only, graph, daily notes, a fresh CSS snippet, opening on Home), owner-facing Start-here.md and Home.md in plain language with Bases dashboard views, routing CLAUDE.md in root and every fold

  • weekly-review

    Scan the vault for this week's activity and write a review file at Resources/Reviews/YYYY-W##.md with a single calibration question. Auto-flags if last week's answer slot was empty. Catches the "vault is decorative" failure mode.

Subagents (3)

  • canon-compressor

    Build the displacement ledger for ONE always-loaded canon file that has tripped its CANON_BUDGETS threshold: tag every rule keep / displace / compress, verify or draft each displaced rule's lessons.md entry, and draft the compressed wording, then STOP at the owner's ruling gate. Follows the canon-sl

  • vault-finding-auditor

    Adversarially verify ONE batch of vault-audit findings BEFORE any remediation acts on them, the read-only gate on the vault-groom fan-out. Re-derives each finding from the vault itself (does the "dead" link really have no target; is the "orphan" really curated and really unlinked; is the missing fro

  • vault-groom-worker

    Apply ONE class of CONFIRMED vault-groom remediations to a bounded batch of files, dotdot-link normalization, exact-rename dead-link repair, derived frontmatter backfill, or orphan tie-in, following the vault-groom skill. Snapshots every canonical file before editing, applies only mechanical fixes w

Hooks (6)

  • SessionStart

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/sb_startup.py"

  • UserPromptSubmit

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/sb_drift.py" prompt

  • PostToolUse

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/sb_drift.py" tool

  • Stop

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/sb_lifecycle.py" stop

  • PreCompact

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/sb_lifecycle.py" precompact

  • SessionEnd

    python3 "${CLAUDE_PLUGIN_ROOT}/hooks/sb_lifecycle.py" end

View source on GitHub

More from maxsheahan/claude-skills

All 14 plugins →

Check whether a finished draft sounds like the person it is supposed to sound like: build a voice profile, score a draft against it, and get one verdict. The grader diagnoses and never edits.

4 skills · 4 agents

0

App-layer security for your builds: ASVS-lite checks (credentialed CORS, stack traces in responses, debug routes, sign-out that only clears the browser, object writes without an ownership reference), outbound-fetch guard against SSRF, abuse and spend (uncapped paid APIs, unset caps that mean unlimited, open proxies, per-client ceilings, caller-set LLM params), auth gates that open on their own (a guard skipped when a secret is unset, identity from a bare header, Access trusted only at the edge, open better-auth sign-up), AI route metering (a daily counter reserved before every paid call, with a drop-in guard template), authorization inside MCP tools (every tool-reachable query scoped to the signed-in identity, no identity from tool arguments, privileged tools gated), and tests proven by removing each protection. Requires secure-core.

7 skills

0

One adapter per supported platform, each stating what it checks and what it cannot see: Cloudflare Pages and Workers (headers on every path, no secrets in [vars], previews off production data, edge hardening), Next.js on OpenNext (server actions, NEXT_PUBLIC_ secrets, static-export headers), Fly and Supabase (RLS, service-role key, [env] secrets, exposed ports), Google Apps Script (web app access, scopes, keys in code), Railway (environment dumps, count-only variable reads), and the Cloudflare account itself through the API or a snapshot (zone SSL, TLS, HTTPS, HSTS, DNSSEC; dangling pages.dev CNAMEs; members without 2FA; preview secrets; orphan KV; data Workers exposed on workers.dev). Requires secure-core.

6 skills

0

The secure-launch front door: maps a repo's attack surface (routes, auth, outbound fetches, paid APIs and their spend caps, secrets by name, data stores, deploy targets), runs every applicable check in the suite, and writes one findings ledger where each check is PASS, FAIL or UNKNOWN. Required by every other secure-launch plugin.

3 skills · 1 command

0

Keep secret values out of repos and out of captured sessions: a gitleaks scan proven on planted keys, values never printed; a staged PreToolUse guard that blocks commands which print secrets; a capture-folder scanner; and a per-provider rotation runbook with a shape check that never displays the value. Requires secure-core.

3 skills

0

Capture a writing voice from a corpus and reproduce it in drafts.

3 skills

0

Similar plugins

caveman

claude

Talk like caveman. Cut filler. Keep technical details explicit.

22 skills · 1 command · 3 agents · hooks

JuliusBrussee/caveman 119,462

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

Taste Skill

claudecodex

tasteskill 2.5.1: professional company websites at the figma.com and x.ai level, with one section per screen, real photographs, real product UI, effects kept for tech and gaming pages, and a real-browser checker and finish gate.

1 skill

Leonxlnx/taste-skill 114,391

career-ops

claudecodex

Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications

5 skills · hooks

career-ops-hq/career-ops 82,253

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

pake

claudecodex

Package any website or local web build into a lightweight desktop app with Pake CLI.

1 skill

tw93/Pake 63,463

Maintain second-brain?

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.

claude & codex plugins14 plugins