mirror of
https://github.com/gnekt/My-Brain-Is-Full-Crew.git
synced 2026-08-27 02:25:35 +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
6.2 KiB
6.2 KiB
Scribe
Your fast-thinking, clean-writing note-taking partner.
What it does
The Scribe turns messy, rushed, half-formed thoughts into clean Obsidian notes. You type fast, you skip punctuation, you mix languages, you abbreviate everything. The Scribe does not care. It takes whatever you throw at it and produces polished, well-structured notes ready for your vault.
It is smart about what it captures. If you dump three unrelated topics in one message, it splits them into three separate notes. If you paste speech-to-text output full of "um" and "like," it cleans it up while keeping your voice. If you are rapid-firing ideas in brainstorm mode, it numbers them all without judging any.
Every note the Scribe creates lands in your Inbox (00-Inbox/), properly formatted with YAML frontmatter, tags, wikilinks to people and projects, and suggested connections to other notes. The Sorter will file them later. The Scribe's job is pure capture speed and quality.
Capabilities
- Standard capture: classifies your input (idea, task, note, person, reference, list) and applies the right template
- Voice-to-note: detects speech-to-text output and cleans it up by removing filler words, restoring punctuation, and preserving your natural voice
- Thread capture: when you send a stream of consciousness, splits it into individual atomic notes linked together
- Quote capture: formats quotes with author, source, page number, and your commentary
- Reading notes: structures book/article/podcast notes with key takeaways, section-by-section summaries, and action items
- Brainstorm mode: captures everything without filtering, numbers ideas, groups by theme, highlights the most promising ones
- Multi-note detection: automatically splits unrelated topics into separate notes
- Emotion tagging: detects emotional tone and tags notes accordingly
- Auto-suggested connections: mentions 2-3 related notes or topics at the end of each note
- Code, math, and diagram support: wraps code in fenced blocks, uses LaTeX for math, creates Mermaid diagrams
- Multilingual: works in any language, handles mixed-language input gracefully
How to use it
Just start typing what you want to capture. The Scribe detects the right mode automatically. You can also be explicit:
- "Save this: [your text]"
- "Quick note: [your text]"
- "Brainstorm: [topic]"
- "Quote: [quote text]"
- "Reading notes for [book/article title]"
- "Thread: [stream of thoughts]"
- "Voice note: [pasted speech-to-text]"
In Italian: "Salvami questo", "Nota veloce", "Appuntati" In French: "Sauvegarde ca", "Note rapide" In Spanish: "Guarda esto", "Nota rapida" In German: "Schnelle Notiz", "Schreib das"
Example conversations
Quick messy capture
You: save this: meeting with Marco, budget discussion, he wants report by friday, also mentioned new hire starting in april, seems worried about Q2 numbers
Scribe: I identified 2 distinct topics and created 2 separate notes:
1. Meeting With Marco, Budget Discussion
Filed as 2026-03-21 - Note - Budget Discussion With Marco.md in 00-Inbox/
Key points captured:
- Marco wants the budget report by Friday
- He expressed concern about Q2 numbers
- Action item: deliver report by Friday
2. New Hire Starting in April
Filed as 2026-03-21 - Note - New Hire April.md in 00-Inbox/
Linked to 05-People/Marco in both notes. Does this capture everything correctly?
Brainstorm mode
You: Brainstorm: ways to improve the onboarding experience for new users
Scribe: Created 2026-03-21 - Brainstorm - Onboarding Improvements.md in 00-Inbox/
Captured all your ideas, numbered and grouped. I noticed 3 natural clusters: UI changes, documentation improvements, and community-driven ideas. The two most promising ideas (based on feasibility and impact) are highlighted in the Hot Takes section.
Want to expand on any of these?
Voice-to-note
You: Voice note: so basically i was thinking about um the whole pricing structure right and like marco said yesterday that we should probably move to a tiered model because uh the enterprise clients are paying the same as the small ones and thats just not sustainable you know so maybe we do three tiers basic pro and enterprise and each one gets different levels of support
Scribe: Detected speech-to-text input. Cleaned and structured as:
Pricing Structure, Tiered Model Proposal
Marco suggested moving to a tiered pricing model because enterprise clients currently pay the same as small clients, which is not sustainable. The proposed tiers:
- Basic: entry level
- Pro: mid-tier
- Enterprise: full support
Each tier would include different levels of support.
Filed as 2026-03-21 - Idea - Tiered Pricing Model.md with source: voice-note in the frontmatter. Sound right?
Works with
- Sorter files the notes the Scribe drops in the Inbox
- Architect provides the templates and naming conventions the Scribe follows. If a new project or area seems to be emerging, the Scribe flags it for the Architect
- Connector gets flagged when the Scribe notices a note relates to many existing notes, so it can do deep linking
Tips
- Do not overthink your input. The messier, the better. That is literally what the Scribe is for. Just dump your thoughts.
- Use "quick dump" for multiple topics. The Scribe will detect and split them automatically.
- Paste raw speech-to-text directly. No need to clean it up first. The Scribe handles filler words, broken sentences, and transcription artifacts.
- Say "brainstorm" when you want zero filtering. The Scribe will capture every idea without judging, then gently highlight the best ones.
- Check the suggested connections. The Scribe adds a Connections section at the end of each note. These are quick wins for building your knowledge graph.
- Trust the assumptions. The Scribe makes judgment calls when your input is ambiguous. It always tells you what it assumed, so you can correct it if needed.
What it remembers
The Scribe keeps a post-it in Meta/states/scribe.md with notes from its last run: which notes it created, brainstorm topics in progress, and assumptions it made. This means if you come back to continue a brainstorm or refine a note, the Scribe already has context.