Files
My-Brain-Is-Full-Crew/skills/defrag/SKILL.md
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

7.2 KiB

name, description
name description
defrag Weekly vault defragmentation. Runs a 5-phase structural audit: inbox hygiene, area completeness, project archival, MOC refresh, tag consistency, structure evolution, and generates a report. Triggers: EN: "defragment the vault", "reorganize the vault", "structural maintenance", "vault defrag", "weekly defrag". IT: "deframmenta il vault", "riorganizza il vault", "manutenzione strutturale", "defrag settimanale". FR: "defragmenter le vault", "reorganiser le vault". ES: "desfragmentar el vault", "reorganizar el vault". DE: "Vault defragmentieren", "Vault reorganisieren". PT: "desfragmentar o vault", "reorganizar o vault".

Weekly Vault Defragmentation

You are executing the Architect's weekly vault defragmentation workflow. This is a structural operation — not a quality audit (that is the Librarian's job). You scan the vault's organizational skeleton, fix structural gaps, evolve the layout, and produce a comprehensive report.

Golden Rule: Language

Always respond to the user in their language. Match the language the user writes in. This skill file is written in English for universality, but your output adapts to the user.


Post-it Protocol

At the START of execution

Read Meta/states/architect.md (if it exists). If it contains an active defrag flow, resume from the recorded phase — do NOT restart from Phase 1.

At the END of execution

Write (or overwrite) Meta/states/architect.md with:

---
agent: architect
last-run: "{{ISO timestamp}}"
---

## Post-it

### Last operation: defrag
### Summary: {{brief summary of what was done}}
### Issues detected: {{any issues that need follow-up, with suggested agents}}

Max 30 lines in the Post-it body. If you need more, summarize.


The 5-Phase Defragmentation Workflow

When the user triggers a defrag, execute all 5 phases in order.

Phase 1: Structural Audit

  1. Scan all files in 00-Inbox/ — anything older than 48 hours that is still in Inbox is a failure. Signal the Sorter via ### Suggested next agent to triage it, or file it yourself if the destination is obvious.

  2. Scan 02-Areas/ — for each area:

    • Does it have an _index.md? If not, create it.
    • Does it have a corresponding MOC in MOC/? If not, create it.
    • Are the sub-folders still relevant? Are there new clusters of notes that warrant a new sub-folder?
    • Are there notes that clearly belong to a different area? Move them.
  3. Scan 01-Projects/ — are there completed projects that should be archived to 04-Archive/?

  4. Scan 03-Resources/ — are there resources that now belong to a specific area? Move them.

  5. Scan MOC/ — is the Master Index up to date? Are all area MOCs linked? Are there MOCs with no corresponding area (orphan MOCs)?

  6. Scan Templates/ — are there templates that are never used? Are there note types that lack a template?

Phase 2: Tag Hygiene

  1. Scan all notes for tags not listed in Meta/tag-taxonomy.md — either add them to the taxonomy or fix them.
  2. Look for tag synonyms (e.g., #ml and #machine-learning) — consolidate.
  3. Ensure hierarchical tags are consistent (all area tags use #area/ prefix).

Phase 3: MOC Refresh

  1. For each MOC, verify that it actually links to the notes it should.
  2. Add links to new notes that were created since the last defrag.
  3. Remove links to notes that were archived or deleted.
  4. Verify that the Master Index (MOC/Index.md) links to every area MOC.

Phase 4: Structure Evolution

  1. Check Meta/user-profile.md — has the user's situation changed? New jobs, new interests, new goals mentioned in recent notes?
  2. If you notice a cluster of 3+ notes on a topic that has no dedicated area or sub-folder, create the structure proactively using the Area Scaffolding Procedure (see below).
  3. Update Meta/vault-structure.md with all changes.

Phase 5: Report

Create a defragmentation report at Meta/health-reports/YYYY-MM-DD — Defrag Report.md:

---
type: report
date: "{{today}}"
tags: [report, defrag, maintenance]
---

# Vault Defragmentation Report — {{date}}

## Summary
- Files moved: {{count}}
- Structures created: {{list}}
- Tags fixed: {{count}}
- MOCs updated: {{list}}
- Inbox items triaged: {{count}}
- Projects archived: {{list}}

## Structural Changes
{{Detailed list of what was created, moved, renamed, or archived}}

## Recommendations
{{Suggestions for the user — new areas to consider, templates to create, etc.}}

## Next Defrag
{{Anything to watch for next week}}

Log the defrag in Meta/agent-log.md.


Area Scaffolding Procedure (Summary)

When Phase 4 detects a new area or sub-area is needed, follow these 7 steps:

  1. Create the folder structure — create the area folder under 02-Areas/ with appropriate sub-folders.
  2. Create the area index note — every area folder gets an _index.md with purpose, active projects, sub-areas, key resources, and a link to its MOC.
  3. Create the area MOC — create MOC/{{Area Name}}.md with overview, structure, key notes, active projects, and a link back to the Master Index.
  4. Update the Master MOC — add a link to the new area MOC in MOC/Index.md.
  5. Create area-specific templates — if the area needs specialized templates (e.g., Finance needs Budget Entry), create them in Templates/.
  6. Update Meta/vault-structure.md — document the new area, its sub-folders, and its purpose.
  7. Update Meta/tag-taxonomy.md — add area-specific tags (e.g., #area/finance, #budget).

For the full detailed procedure with templates and examples, see the Architect agent (agents/architect.md, Section 4).


Inter-Agent Coordination

After completing the defrag, analyze your findings and suggest follow-up agents when appropriate. Include a ### Suggested next agent section at the end of your output for each applicable case:

  • Sorter — when Inbox has items older than 48 hours, or when notes in 03-Resources/ should be moved to a newly created area.
  • Connector — when new MOCs were created that need linking, or when orphan notes (no links) were found.
  • Librarian — when structural inconsistencies were found that need a full quality audit (broken links, duplicates).

Output format for suggestions

### Suggested next agent
- **Agent**: sorter
- **Reason**: {{why this agent should run next}}
- **Context**: {{specific details about what needs attention}}

When to suggest a new agent

If during defrag you detect a recurring need that no existing agent covers, include:

### Suggested new agent
- **Need**: {{what capability is missing}}
- **Reason**: {{why no existing agent can handle this}}
- **Suggested role**: {{brief description of what the new agent would do}}

Output Format

Always structure your response as follows:

  1. Announce the defrag is starting (in the user's language)
  2. Execute each phase, reporting findings as you go
  3. Generate the report file at Meta/health-reports/
  4. Update your post-it at Meta/states/architect.md
  5. Log the operation in Meta/agent-log.md
  6. Summarize results to the user with key metrics (files moved, structures created, tags fixed, MOCs updated)
  7. Suggest next agents if applicable