mirror of
https://github.com/gnekt/My-Brain-Is-Full-Crew.git
synced 2026-08-26 02:04:43 +00:00
1ee2dc415f
* Add standardized template for custom agent creation
New file: references/agent-template.md
This is a reference document that the Architect reads when generating
custom agents. It defines the exact structure every agent must follow:
YAML frontmatter format, required sections (Language, User Profile,
Inter-Agent Coordination, Core Responsibilities, Operational Rules),
placeholder tokens, and inline conventions (naming rules, tool
permissions, multilingual triggers).
The template is not an agent itself. It is a structural guide that
ensures custom agents are generated with the same quality and
consistency as the core 8.
* Add custom agent support to orchestration references
agents-registry.md:
- Added "Custom Agents" section with rules for how custom agents
are added to the registry (naming, priority, creation flow)
- Custom agents always have lower priority than core 8
- Names must be lowercase with hyphens, no conflicts with core names
agents.md:
- Added "Custom Agents" section explaining what they are, how they
coordinate with core agents, and how to create/edit/remove them
agent-orchestration.md:
- Added "Suggested new agent" signal format so agents can flag when
the user needs functionality that no existing agent provides
- Added step in Dispatcher Decision Logic to check for this signal
- Added "Custom Agent Lifecycle" section covering creation, discovery,
routing, chaining, maintenance, and deletion
* Add "Suggested new agent" capability to all 7 non-architect agents
Each agent now has a "When to suggest a new agent" subsection inside
its Inter-Agent Coordination block. When an agent detects that the
user needs functionality that no existing agent can handle, it
outputs a "Suggested new agent" section with:
- Need: what capability is missing
- Reason: why no existing agent covers it
- Suggested role: what the new agent would do
The dispatcher reads this and asks the user if they want the
Architect to create a custom agent for the detected need.
Agents are also told when NOT to suggest a new agent (existing
agent can handle it, one-off task, outside vault scope).
* Add full custom agent creation flow to the Architect
The Architect can now create, edit, and remove custom agents through
an extended conversational flow with the user.
Changes to the frontmatter:
- Added trigger phrases for custom agent creation in 6 languages
("create a new agent", "custom agent", "crea un nuovo agente", etc.)
New section "Custom Agent Creation" with:
- 5-phase conversation flow (Understanding, Capabilities, Output,
Advanced, Confirmation) where the Architect asks one question at
a time and adapts follow-ups based on user answers
- Agent file generation following references/agent-template.md
- Automatic updates to agents-registry.md and agents.md
- Management commands: edit, remove, list custom agents
- Validation rules: no name conflicts with core 8, minimal tool
permissions by default, mandatory coordination sections
- Quality standards: Core Responsibilities must be detailed enough
to produce a production-quality agent
Also added the "Suggested new agent" subsection (same as other agents).
* Update dispatcher routing to support custom agents
- Changed "The ONLY agents you may use are these 8" to acknowledge
that custom agents created by the Architect are also valid
- Added row 9+ to the routing priority table for custom agents
(always lower priority than core 8)
- Added section 9 "CUSTOM AGENTS" with routing logic: when no core
agent matches, check agents-registry.md for custom agents
- Added check for "Suggested new agent" signals in the multi-agent
routing decision flow (step 6)
* Add custom agents to README, CONTRIBUTING, and TERMS_OF_USE
README.md:
- Badge changed from "8 Agents" to "8+ Agents"
- Added custom agents as point 4 of "What makes this different",
positioned right after the main pitch for maximum visibility
- Includes a table of real-life scenarios (budget tracking, journaling,
paper reading, project monitoring, client deadline management)
- Links to Terms of Use for the responsibility disclaimer
CONTRIBUTING.md:
- Renamed "Propose a new crew member" to "Propose a new core crew
member" with a note that users can create custom agents via Architect
- Added "Custom agents vs. core agents" section explaining the
distinction between personal custom agents and project-shipped
core agents
TERMS_OF_USE.md:
- Added new Section 9 "Custom Agents" with full disclaimer: custom
agents are entirely the user's creation and responsibility, no
warranty on their behavior, author accepts no liability
- Updated Section 7 (Limitation of Liability) to reference custom
agents explicitly
- Renumbered sections 9-11 to 10-12
* Force the Architect to always run the full conversation before creating a custom agent
The Architect was generating custom agents immediately from a single
user message instead of going through the 5-phase conversation flow.
Added explicit blocking instructions at three points:
- Section intro: "NEVER create an agent in one shot"
- Before the conversation phases: "Do NOT generate the agent
immediately, even if the request seems clear"
- Explicit rule: "You are NOT allowed to create the agent file
until Phase 5"
- Reinforced one-question-per-message rule
* Force custom agent descriptions to use only the user's language
The Architect was copying the multilingual pattern from core agents
and adding translations in 6+ languages to custom agent descriptions.
Custom agents should have their description and trigger phrases
written exclusively in the language the user speaks. Reinforced
this rule in both the generation instructions and the validation
rules section.
* Force custom agent body to always be written in English
The frontmatter description uses the user's language (for trigger
matching), but the agent body (system prompt) must always be in
English for better LLM instruction-following performance. The agent
still responds in the user's language at runtime thanks to the
language matching rule.
* Add confirmation prompt before overwriting existing installation
launchme.sh:
- Detects if .claude/ or CLAUDE.md already exist in the vault
- Shows the user what will be overwritten
- Asks for explicit confirmation before proceeding
- Clarifies that custom agents and vault notes are never touched
updateme.sh:
- Asks for confirmation before overwriting core files
- Same clarification about custom agents being preserved
* Deprecate removed files instead of leaving orphans in the vault
When a file is removed from the repo (agents, references, or skills),
the updater now renames it with a "-DEPRECATED" suffix and prepends
a "DEPRECATED DO NOT USE" header instead of silently leaving it.
updateme.sh:
- Core agents in .claude/agents/ that no longer exist in the repo
get renamed to {name}-DEPRECATED.md with deprecation header
(custom agents are never touched)
- References in .claude/references/ that no longer exist in the repo
get the same treatment
- The entire .claude/skills/ directory (removed from the project)
gets renamed to .claude/skills-DEPRECATED/ with deprecation headers
on each SKILL.md
- Summary now reports deprecated file count
launchme.sh:
- Added confirmation prompt before overwriting existing installation
- Skills generation and copying kept intact (generate-skills.py runs
first, then copies to .claude/skills/)
* Add first-run setup section to custom agent template and creation flow
Custom agents now have a "First Run Setup" section that defines what
the agent must do the very first time it is invoked: what questions
to ask the user, what config files or folders to create, and how to
detect that it has already been set up.
agent-template.md:
- New "First Run Setup" section between Core Responsibilities and
Operational Rules, with subsections for detection, questions to
ask, what to create, and post-setup behavior
architect.md:
- New Phase 4 "First Run Setup" in the conversational flow where
the Architect asks the user what the agent should do on first run
- Previous Phase 4 (Advanced) becomes Phase 5
- Previous Phase 5 (Confirmation) becomes Phase 6
- Updated blocking rules to reference Phase 6
* Redesign README header and broaden legal disclaimers for custom agents
Improve README header visual hierarchy: centered title, prominent Discord
CTA, metadata badges moved to secondary row. Replace two custom agent
examples with funnier, gender-neutral ones. Rewrite TERMS_OF_USE Section 3
from "Health and Wellness Agents" to "Custom Agents and Advice-Generating
Output" covering health, legal, financial, and all regulated domains.
* Fix reference paths in architect to use .claude/references/ prefix
The agent runs inside the vault where references live under
.claude/references/, not under references/ (which is the repo layout).
* Fix reference paths in agent-template to use .claude/references/ prefix
* Add core-manifest to protect custom agents from deprecation
launchme.sh and updateme.sh now write .core-manifest listing which agent
files were installed as core. The deprecation loop checks this manifest
before touching any file, so custom agents are never deprecated.
* Skip agent deprecation if target DEPRECATED file already exists
* Include skill count in updateme.sh summary condition and message
* Fix agents-registry.md paths in CLAUDE.md to use .claude/references/ prefix
* Add edit/remove/list trigger phrases to custom agent routing
* Deprecate stale core agents on reinstall before copying new ones
On reinstall (EXISTING=1), read the old .core-manifest and deprecate
any agent that is no longer shipped in the repo, before writing the
new manifest. Prevents stale core agents from lingering in the vault.
* Fix custom agent description: triggers are in user's language, not multilingual
* Fix updateme.sh: deprecate stale agents before rewriting manifest
The manifest was being truncated and rewritten before the deprecation
loop ran, so removed core agents were no longer in the manifest and
got skipped as "custom". Now: read old manifest -> deprecate -> copy
new agents -> rewrite manifest.
* Fix grep exit code handling when removing last entry from manifest
* Fix nested fenced code blocks in agent-template using tildes
* Add core-manifest for references to protect user-created reference docs
Same pattern as agents: launchme/updateme write a .core-manifest in
.claude/references/ listing installed core files. The deprecation loop
only touches files in the manifest, leaving user-created references
untouched.
* Move deprecated files to .claude/deprecated/ to prevent auto-discovery
Deprecated agents kept in .claude/agents/ could still be auto-discovered
by Claude Code via their frontmatter. Moving them to .claude/deprecated/
ensures they are completely invisible to the dispatcher while still
preserved for user reference.
* Harden updateme.sh from Copilot review feedback
Address multiple issues raised during PR code review:
- Skip deprecation entirely when .core-manifest is missing, preventing
accidental deprecation of custom agents/references on first update
- Preserve user's "## Custom Agents" sections in agents-registry.md and
agents.md during reference updates (merge strategy instead of overwrite)
- Update confirmation message to accurately reflect what is preserved
* Preserve custom agent content during install and update
- launchme.sh: skip overwriting agents-registry.md and agents.md on
reinstall to preserve custom agent entries
- updateme.sh: extract and re-insert custom table rows from the
registry table plus custom sections, preventing data loss when
updating from upstream
- Require manifest before deprecating to avoid false positives
* Update wardrobe-coach example phrase in README
* Use robust string matching and printf for user-mutable refs
- Replace grep -qw with bash substring match for filename detection
- Replace echo with printf '%s\n' to prevent content mangling
* Enforce step-by-step conversation in Architect and fix registry row reinsertion
- Add HARD CONSTRAINT blocks to both onboarding and custom agent creation
flows, forcing the use of AskUserQuestion for each question to prevent
the Architect from skipping phases or bundling questions
- Replace hard-coded "| postman |" match in updateme.sh with generic
last-table-row detection to avoid breaking custom row reinsertion if
core agents are renamed or reordered
* Improve input handling in launchme.sh and updateme.sh for non-interactive shells
* Extract 13 skills from agents and update full documentation
Architecture change: complex multi-step flows (onboarding, email triage,
transcription, etc.) are now skills that run in the main conversation
context instead of agent subprocesses. This fixes the state/context loss
that caused agents to skip phases during multi-turn conversations.
Skills created (13):
- Architect: /onboarding, /create-agent, /manage-agent, /defrag
- Postman: /email-triage, /meeting-prep, /weekly-agenda, /deadline-radar
- Transcriber: /transcribe
- Librarian: /vault-audit, /deep-clean, /tag-garden
- Sorter: /inbox-triage
Agent changes:
- architect.md: -70% (1554 → 473 lines)
- transcriber.md: -72% (530 → 147 lines)
- postman.md: -42%, librarian.md: -37%, sorter.md: -11%
- All agents: explicit post-it create-if-not-exists
Scripts:
- launchme.sh/updateme.sh: copy skills/ directly, remove generate-skills.py
Docs updated:
- README.md: new Skills section, mermaid diagrams, routing
- getting-started.md, examples.md: skill references
- docs/agents/*.md: capability tables with skill vs agent routing
- references/agents.md, agent-orchestration.md, agents-registry.md,
agent-template.md: skill registry, skill-first routing protocol
6.6 KiB
6.6 KiB
Connector
The agent that turns isolated notes into a living knowledge web.
What it does
The Connector is obsessed with relationships between your notes. It reads your vault, analyzes the link structure, and finds connections you did not know existed. That meeting note from January? It relates to the idea you jotted down last week. That book quote? It supports the argument in your project brief. The Connector sees these threads and weaves them together.
Your vault's value grows exponentially with the quality of its connections. A note with zero links is an island, useful on its own but invisible to everything around it. The Connector ensures no note stays isolated for long. It discovers missing links, suggests new connections ranked by confidence, identifies clusters of related notes that need a Map of Content, and can even surprise you with unexpected relationships between seemingly unrelated topics.
It is also your graph health monitor. It tracks metrics like orphan rate, link density, and cluster count, and tells you when parts of your vault are drifting into isolation.
Capabilities
- Full graph audit: maps all wikilinks, identifies orphan notes (no incoming links), dead-end notes (no outgoing links), and disconnected clusters
- Targeted connection discovery: given a specific note, finds all potentially related notes ranked by strength (strong, medium, weak)
- Serendipity mode: discovers unexpected connections between notes that share no obvious keywords but relate conceptually
- Semantic bridging: finds notes about the same concept using different terminology
- Bridge notes: creates new notes that explicitly connect two otherwise separate clusters
- MOC enhancement: audits Maps of Content for completeness and suggests missing entries
- Constellation view: shows how a topic connects across different areas of your vault (work, personal, learning)
- People network: maps how people in your vault are connected through meetings, projects, and references
- Graph health metrics: tracks connectivity ratio, orphan rate, average path length, cluster count, and MOC coverage
- Batch processing: after the Sorter files a batch of notes, analyzes all of them for connections at once
How to use it
Trigger the Connector when you want to strengthen your vault's knowledge graph:
- "Find connections for my latest note"
- "Analyze my vault graph"
- "What notes are isolated?"
- "What connects [topic A] and [topic B]?"
- "Find missing links"
- "Surprise me, what unexpected connections exist?"
- "Audit the MOCs"
- "How is my graph health?"
- "Show me the people network"
In Italian: "Trova connessioni", "Analizza le relazioni", "Collega le note" In French: "Trouve des connexions", "Analyse du graphe" In Spanish: "Encuentra conexiones", "Analiza el grafo" In German: "Finde Verbindungen", "Netzwerkanalyse"
Example conversations
Connection discovery for a specific note
You: Find connections for my latest note on tiered pricing
Connector: I analyzed "Tiered Pricing Model" and found these potential connections:
Strong (add these):
- Client Feedback on Pricing contains the client's response to the tiered model idea
- Sprint Planning Q2 is the meeting where Marco first proposed the tiers
Medium (probably useful):
- Competitor Analysis Q1 includes competitor pricing models for comparison
- Revenue Projections 2026 would be impacted by a pricing change
Weak (worth considering):
- Reading Notes, SaaS Pricing Strategies has book notes with relevant frameworks
Want me to add the strong connections now?
Graph health check
You: How is my graph health?
Connector: Vault Graph Analysis
Stats:
- Total notes: 147
- Total links: 312
- Average density: 2.1 links per note
- Orphan notes: 18 (12%), target is under 10%
- Dead-end notes: 9
Islands (disconnected clusters):
- "Personal Finance": 5 interconnected notes, 0 external links
- "Old Project Beta": 8 notes, only 1 link to the rest of the vault
Top 5 most connected notes:
- MOC/Index, 23 links out
- Sprint Planning Q2, 8 links in, 6 links out
- Project Alpha Roadmap, 5 links in, 9 links out
Recommendations:
- The Personal Finance cluster should be linked to your Areas and daily notes
- 18 orphan notes need attention. Want me to suggest connections for each?
Serendipity mode
You: Surprise me, what unexpected connections exist?
Connector: Here are some connections you probably did not expect:
-
Your reading notes on "Atomic Habits" and your project retrospective for Beta share the same core insight about feedback loops, one in personal habits, one in software development. Linking them could create a powerful cross-domain concept note.
-
Three different people in your vault (Marco, Sarah, and the podcast guest from last week) all independently mentioned the same concern about "sustainable growth." This might be an emerging theme worth a dedicated note.
Want me to create any of these connections?
Works with
- Sorter: after a batch filing, the Connector receives a notification to analyze newly filed notes
- Architect: when the Connector discovers a cluster needing a new MOC, it flags the Architect to create one
- Seeker: the Connector can ask the Seeker to verify content-level relationships before suggesting links
- Librarian: broken wikilinks found during analysis are reported to the Librarian
Tips
- Run it after big filing sessions. The best time to use the Connector is right after the Sorter processes a batch of notes. The new notes have the most linking potential.
- Start with "strong" connections. When the Connector suggests links at three confidence levels, always approve the strong ones. They are almost always correct.
- Use serendipity mode for creative work. The unexpected connections it finds can spark genuinely new ideas by linking concepts from different domains.
- Watch the orphan rate. If it climbs above 15-20%, your vault is accumulating unlinked knowledge that is effectively invisible. Run a graph audit.
- Do not over-link. The Connector follows a quality-over-quantity principle. A few meaningful links are worth more than dozens of superficial ones. Trust its judgment.
- Check the people network. It is a surprisingly useful way to see who appears most often in your vault and how they are connected to your projects.
What it remembers
The Connector keeps a post-it in Meta/states/connector.md with notes from its last analysis: links it created, orphan notes still unconnected, emerging clusters, and connection suggestions the user deferred. This gives it a head start on the next graph analysis.