mirror of https://github.com/gnekt/My-Brain-Is-Full-Crew.git synced 2026-08-27 18:45:45 +00:00

Files

Gnekt 1ee2dc415f Add custom agent system with orchestration, templates, and broadened legal coverage (#21 )

* 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

2026-03-25 12:00:00 +01:00

6.1 KiB

Raw Permalink Blame History

Seeker

Ask your vault a question. Get an answer with sources.

What it does

The Seeker is your vault's search engine and research assistant rolled into one. It does not just find files; it understands questions. Ask "What did we decide about pricing?" and it searches across meeting notes, project files, and email imports to synthesize an answer with source links. Ask "Find all notes about Marco from this month" and it queries by person, date range, and content.

The Seeker searches everything: file contents, filenames, YAML frontmatter, tags, wikilinks, and relationship graphs. It ranks results by relevance, separates high-quality matches from tangential ones, and presents everything in a clean, scannable format. When it finds nothing, it suggests alternative searches, checks for typos, and offers to create a new note on the topic.

Beyond searching, the Seeker can also modify existing notes by updating content, adding tags, fixing broken links, or appending new information. It always reads the full note first and confirms changes before making them.

Capabilities

Full-text search: searches file contents with keyword and phrase matching
Metadata search: queries by type, date range, tag, person, project, or status
Relationship search: navigates the wikilink graph (forward links, backlinks, common connections)
Answer mode: synthesizes information from multiple notes to answer a question, with source citations
Timeline mode: finds notes within a date range, useful for "what happened last week" queries
Diff mode: compares versions of a topic across different notes to spot contradictions or evolution
Missing knowledge detection: identifies gaps in your vault (topics mentioned but never explained)
Note modification: append, update, refactor, re-tag, or fix links in existing notes
Cross-reference answering: pulls data from multiple sources and presents a unified answer

How to use it

Ask any question about your vault, or search for specific content:

"What did we decide about [topic]?"
"Find all meeting notes from March"
"What do I know about [topic]?"
"Find notes tagged #marketing"
"What notes mention Marco?"
"Where did I put the note about [subject]?"
"What am I missing about microservices?"
"Update the note about [topic] with [new info]"
"What connects Marketing and Sales in my vault?"

In Italian: "Cerca nel vault", "Trova", "Dove ho messo", "Che note ho su" In French: "Cherche dans le vault", "Trouve" In Spanish: "Busca en el vault", "Encuentra" In German: "Suche im Vault", "Finde"

Example conversations

Answer mode

You: What did we decide about the pricing model?

Seeker: Based on your notes, here is what I found about pricing decisions:

Marco proposed moving to a tiered pricing model (Basic, Pro, Enterprise) during the Sprint Planning on March 18. The main driver is that enterprise clients currently pay the same as small clients. The client feedback note from March 20 suggests the client is open to tiered pricing but wants volume discounts included.

No final decision has been recorded yet. The next step appears to be delivering the pricing report by Friday (March 22).

Sources:

06-Meetings/2026/03/Sprint Planning Q2 (initial proposal)
02-Areas/Sales/Client Feedback on Pricing (client response)
00-Inbox/Tiered Pricing Model (Marco's voice note with details)

Finding notes by criteria

You: Find all meeting notes from this month with open action items

Seeker: Found 5 meeting notes from March 2026 with uncompleted action items:

Missing knowledge

You: What am I missing about microservices?

Seeker: You have 4 notes that mention microservices, but I notice some gaps:

You have covered:

Architecture decision to adopt microservices (from a meeting note)
Service mesh comparison (from reading notes)

Missing or thin:

No notes on deployment strategy or CI/CD for microservices
No notes on monitoring and observability
The meeting note references a "microservices RFC" that does not exist in your vault

Would you like to create notes for any of these gaps, or search for related content that might cover them indirectly?

Works with

Sorter: the Seeker can verify whether similar notes already exist before the Sorter files new ones
Connector: when the Seeker finds unlinked but related notes, it flags them for the Connector
Librarian: the Seeker often discovers broken links, orphan notes, or frontmatter problems while searching
Scribe: if a search reveals missing knowledge, the Seeker can suggest creating a new note via the Scribe

Tips

Ask questions, not just keywords. The Seeker is best when you ask "What do I know about X?" rather than just typing "X."
Use it for decision archaeology. "What did we decide about Y?" is one of the most powerful queries. It searches across meetings, emails, and project notes.
Request a timeline. Saying "Show me everything about project Alpha in chronological order" gives you the full story of a project.
Ask about gaps. "What am I missing about [topic]?" triggers the missing knowledge detector, which is surprisingly useful for learning and project planning.
Combine criteria. "Find all notes tagged #urgent that mention Marco from the last two weeks." The Seeker handles compound queries.
Use it to update notes. Instead of finding a note and editing it yourself, tell the Seeker: "Update the note about X with this new info."

What it remembers

The Seeker keeps a post-it in Meta/states/seeker.md with notes from its last search: what you searched for, what was found (or not), and recurring topics. This helps it refine future searches and flag vault gaps it has noticed over time.

6.1 KiB Raw Permalink Blame History