agent-peer
claudecodexDaemonless local messaging between Claude Code and Codex CLI sessions on macOS, Linux, and Windows.
4 skills
A knowledge vault Claude reads and keeps for any folder of notes: graph-indexed vault tools, private domains that stay sealed, connections to what you already wrote surfaced under answers, and [[note]] links in replies that are checked against the vault.
Plugin commonplace from marketplace stray-bits-sanctuary in noopz/stray-bits-sanctuary. Commands read from the repo's manifest — 17 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.
autoimproveAutonomous vault improvement loop (writes changes). Use when user says 'improve the vault', 'autoimprove', 'fix what you can', 'what's the vault score'. Do NOT use for read-only diagnostics — that's wiki-lint.
paper-analyzerDeep paper breakdown (does not write vault notes). Use when user says 'analyze this paper', 'break down this paper', 'is this paper any good', or sends an arXiv ID/PDF with no save intent. Do NOT use when user wants the paper saved — that's wiki-ingest.
vault-skillRun one of the vault's own Claude Code skills (its .claude/skills/, e.g. a YouTube or project intake) from a session started outside the vault. Use when the user names a vault skill or asks to "run <name> from my vault".
wiki-compileFill concept stubs with citation-grounded definitions. Use when user says 'fill in the stubs', 'compile concepts', 'flesh out concepts', or as follow-up after wiki-lint reports stubs. Do NOT use for new sources not yet in vault — that's wiki-ingest.
wiki-deep-linkUser-invoked: surface hidden concept connections via local embeddings (Ollama + nomic-embed-text). Flags related-but-unlinked (sentence, concept) pairs, then adds wikilinks where the connection holds. Invoke explicitly via /wiki-deep-link.
wiki-domainSet up, list, rename, or merge research domains. Use when user says 'add a domain for X', 'set up a domain', 'what domains exist', 'change scope of X domain', 'merge X and Y domains'. Do NOT speculatively fire on ingest prompts — wiki-ingest hands off explicitly when no domain matches.
wiki-ingestALWAYS use when the user wants a source saved to the vault — pastes an arXiv ID/URL, says 'add this to the vault', 'save this', 'remember this', 'I found this interesting', or describes a specific finding/technique/project to capture. Do NOT activate for general topic conversation — only when there'
wiki-initUser-invoked setup: point commonplace at a folder for the first time or reconfigure the active vault. Writes the vault marker, scaffolds `.wiki/`, discovers initial domains/genres. Invoke explicitly via /wiki-init.
wiki-lintRead-only vault health check. Use when user says 'how's the vault', 'audit', 'lint', 'anything broken', 'show me broken links/stubs/orphans'. Do NOT use when user wants fixes applied — hand off to autoimprove.
wiki-queryAnswer questions from vault notes. Use when user asks 'how does X relate to Y', 'what do the papers say about Z', 'compare approaches to W', or discusses concept connections. Also fire immediately after wiki-ingest when user pivots from saving to asking how the new source relates to other vault topi
wiki-supersedeRetire/replace a vault entity. Use when user says 'mark X retired', 'switched from X to Y', 'Y supersedes X', 'Y replaces X', or when another skill flags retired-but-live mentions. (Post-write hook auto-surfaces this when a note body declares supersession.) Do NOT use for typo renames, stale-link cl
paper-methodology-analystAnalyzes a research paper's methodology section in depth from extracted text. Dispatched by the paper-analyzer skill during multi-stage paper analysis. Produces a structured breakdown of research design, datasets, baselines, metrics, setup, and limitations with specific numbers and table references.
paper-reflection-agentReviews a combined paper-analysis (methodology + results) for completeness and quality, scores it 0–100, and identifies specific gaps for revision. Dispatched by the paper-analyzer skill as the final reflection pass before the analysis is committed to the vault.
paper-results-interpreterInterprets a research paper's results tables, figures, and claims to validate whether conclusions follow from the data. Dispatched by the paper-analyzer skill during multi-stage paper analysis. Produces a quantitative breakdown with specific numbers, claim validation, and flagged overstatements.
wiki-conventions-tunerProposes per-genre quality rules for `.wiki/conventions.json` by reading sample notes from each genre and synthesizing patterns the user actually uses. Dispatched directly by the user, by the indexer when new genres cross the 3-note threshold without rules, or in response to a SessionStart warning a
wiki-cross-domain-linkerIdentifies cross-domain concept bridges surfaced by a newly ingested source and adds connection callouts to affected notes in other domains. Dispatched after wiki-ingest when `cross-domain.ts` reports bridge concepts. Receives the script's JSON output inline.
wiki-deep-linkerReviews semantic-similarity candidates from `commonplace deep-link` — (sentence, concept) pairs that embeddings flagged as related but unlinked — and adds wikilinks where the connection holds up under reading. Dispatched by autoimprove or directly when the user asks for deep-linking. Edit-only, neve
wiki-domain-managerReviews and configures domain scope and linkGroup settings in `.wiki/domains.json`. Dispatched after `commonplace init` discovers new domains, when the indexer auto-discovers a new domain, or when the user asks to manage domain configuration.
wiki-freshness-checkerChecks whether live source URLs have changed significantly since the vault note was written, and adds a `> [!stale]` callout to notes whose source content has substantially diverged. Dispatched by autoimprove's post-loop freshness step with a candidates JSON from `commonplace freshen --sample`.
wiki-impact-checkerChecks whether a newly ingested source note changes or extends conclusions in existing source notes that share the same concepts, and surfaces supersession candidates. Dispatched by the post-write hook after wiki-ingest creates a new source note.
wiki-linterFixes mechanical lint issues in the vault — malformed dates, stale MOC counts, duplicate frontmatter entries. Deterministic fixes only; never writes definitions or synthesizes content. Dispatched by autoimprove with the lint output inline.
wiki-moc-splitterSplits an oversized MOC into themed sub-MOCs and turns the parent into an index-of-sub-MOCs hub. Dispatched by autoimprove when the moc-size lint check reports a MOC over the hard cap, or directly when the user asks to split a MOC.
wiki-moc-updaterKeeps Maps of Content (MOCs) in sync with the source notes that reference them — adds missing source entries, updates counts, and fixes stale links. Dispatched after wiki-ingest creates a new source note, and by autoimprove for stale-MOC rounds.
wiki-prunerRemoves low-value concept stubs from the vault and cleans up their references. Executes the deterministic decisions made by `commonplace prune` — never makes value judgments. Refuses to prune retired notes (routes to wiki-supersede instead). Dispatched by autoimprove during pruning rounds.
node "${CLAUDE_PLUGIN_ROOT}/bin/commonplace" session-check 2>/dev/null || true
Daemonless local messaging between Claude Code and Codex CLI sessions on macOS, Linux, and Windows.
4 skills
Entropy-guided structural outlines for Claude Code — compresses large file reads by ~83% without parsing, using BSP trees and Shannon entropy to serve navigable file maps instead of full content
hooks
Generate natively editable PPTX from PDF / DOCX / URL / Markdown — real DrawingML shapes, text boxes, charts, and animations. Note: run `pip install -r requirements.txt` inside the installed plugin directory for the Python post-processing scripts to work.
1 skill
Claude Skills for Obsidian
6 skills
Manage the Carta CRM conversationally — search, add, update, and enrich investors, companies, contacts, deals, notes, and fundraisings via the Carta CRM MCP Server.
28 skills · hooks
HADS (Human-AI Document Standard) — semantic tagging convention for docs that work for both humans and AI models — plus the grounded-vault pattern for provenance-linked, drift-checked knowledge stores.
2 skills
Earnings call and filings to model update to note draft
6 skills · 1 agent
Manage the Carta CRM conversationally — search, add, update, and enrich investors, companies, contacts, deals, notes, and fundraisings via the Carta CRM MCP Server
28 skills · hooks
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.