Files
My-Brain-Is-Full-Crew/tests/regression/snapshot/.claude/skills/defrag/SKILL.md
Giacomo Nunziati 53b605379e feat: multi-platform adapter architecture (Claude Code, Gemini CLI, OpenCode) (#32)
* Fix istall/update scripts

* test: capture pre-refactor install snapshot for regression

Adds take-snapshot.sh script and the resulting snapshot/ directory,
capturing the exact vault state produced by launchme.sh before the
framework-agnosticity refactor begins.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Summary: Refactor agents/skills/hooks/mcp in agentic-platform-agnostic templates.

refactor: rename source CLAUDE.md → DISPATCHER.md (framework-neutral)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

refactor: convert agent frontmatter from tools: to neutral capabilities:

Replace Claude Code-specific `tools:` frontmatter with framework-agnostic
`mode: subagent` and `capabilities: [...]` in all 8 agent files.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

refactor: add neutral hook trigger manifests (.hook.yaml)

refactor: hooks read neutral JSON schema (args.* instead of tool_input.*)

refactor: convert .mcp.json to neutral mcp/servers.yaml

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Implement agentic-platform adapters skeleton.

build: add adapters/lib.sh skeleton with vocabulary constants

test: bash test runner for adapter helpers

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

build(adapters): parse_frontmatter helper with tests

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

build(adapters): parse_capabilities helper with tests

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

build(adapters): should_include helper with tests

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

build(adapters): parse_hook_yaml helper with tests

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

build(adapters): agent_body helper with tests

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

build(adapters): enumerate_agents and enumerate_hooks helpers

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Implement agentic-platform adapter for Claude Code.

build(adapters): claude-code adapter skeleton with capability/event tables

build(claude-code): adapter_translate_dispatcher with test

build(claude-code): adapter_translate_references with test

build(claude-code): adapter_translate_skills with tests

build(claude-code): adapter_translate_agents with capability→tools mapping

build(claude-code): hook wrapper template (CC native → neutral schema)

build(claude-code): adapter_translate_hooks with wrapper generation

build(claude-code): adapter_translate_mcp with hand-rolled YAML parser

build(claude-code): adapter_finalize and complete adapter_build wiring

build: scripts/build.sh dispatches to per-framework adapter

Also fix adapter_translate_hooks and adapter_translate_agents to use
while-read loops (avoiding word-splitting on paths with spaces) and
guard grep calls with || true to survive set -eo pipefail when hooks
have no match-tool field. Remove scripts/build.sh from .gitignore.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Refactor install/update scripts to support agentic-platform agnosticity.

refactor(lib.sh): generalize install_claude_md → install_dispatcher

New signature takes the full destination path instead of just the vault
dir, allowing callers to install CLAUDE.md, AGENTS.md, or any dispatcher
file to an explicit location.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

feat(launchme): support --framework flag, build dist/ before install

Add --framework and --target arg parsing. Run build.sh before installing
to populate dist/<framework>/. All install_* calls now read from
dist/<framework>/ instead of the raw source dirs. MCP is now handled
automatically by the adapter (no interactive prompt). Replaced
install_claude_md with install_dispatcher.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

feat(updateme): support --framework flag, build dist/ before update

Add --framework and --target arg parsing. Run build.sh before installing
to populate dist/<framework>/. All install_* calls now read from
dist/<framework>/ instead of raw source dirs. Replaced install_claude_md
with install_dispatcher.

Also fix set -e compatibility in lib.sh: add || true to all conditional
[[ ... ]] && info "..." logging lines so they don't abort the script
when VERBOSE_COPY=0.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* test: regression runner diffs dist/claude-code against pre-refactor snapshot

- Add tests/regression/run.sh that builds dist/claude-code and compares
  against snapshot, excluding runtime-only artifacts (.mbifc-manifest,
  .mcp.json, .claude-plugin/plugin.json)
- Fix adapters/lib.sh agent_body: preserve '---' section dividers in body
  (awk now only skips '---' while still inside frontmatter, fm < 2)
- Fix adapters/claude-code/adapter.sh: change 'read' capability to expand
  to only 'Read', appending 'Glob, Grep' at end of tools list to match
  snapshot ordering
- Update snapshot to reflect intentional refactor changes: hook JSON schema
  (.args.* instead of .tool_input.*), wrapper scripts, settings.json with
  wrapper paths, and consistent tool ordering for postman/sorter

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Implement opencode adapter.

Co-Authored-By: win0na <winnie@winneon.moe>

feat(lib.sh): add install_plugins helper for opencode JS plugins

build(adapters): opencode adapter skeleton with capability/event tables

build(opencode): adapter_translate_dispatcher (DISPATCHER.md → AGENTS.md)

build(opencode): adapter_translate_references and adapter_translate_skills

Implements Task 4 and Task 5:
- adapter_translate_references: Copies reference markdown files to .opencode/references/
- adapter_translate_skills: Copies skill SKILL.md files to .opencode/skills/<name>/ with exclude filtering

Both functions respect framework filtering via should_include().

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

build(opencode): adapter_translate_agents with capability→permission mapping

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

build(opencode): bash-executor template for spawning hook scripts

build(opencode): plugin-stub template for mbifc-hooks.js

build(opencode): adapter_translate_hooks with JS plugin generation

Implements _oc_hook_registry_json and adapter_translate_hooks in the
opencode adapter. Copies hook scripts to .opencode/hooks/, generates a
single .opencode/plugins/mbifc-hooks.js by inlining bash-executor.js and
synthesising a hook registry from *.hook.yaml files. Uses python3 for
template substitution to safely handle multi-line JS content. Adds 3
unit tests (copies scripts, registry entries, noop when no hooks dir).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

build(opencode): adapter_translate_mcp with local/remote handling

build(opencode): adapter_finalize and complete adapter_build wiring

Add adapter_finalize placeholder and wire adapter_translate_mcp into
adapter_build; add end-to-end integration test (14/14 pass).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

feat(launchme): branch on --framework for opencode install layout

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

feat(updateme): branch on --framework for opencode install layout

Mirror the same case "$FRAMEWORK" block from launchme.sh: framework-specific
DIST_COMPONENTS_DIR, VAULT_COMPONENTS_DIR, DISPATCHER_SRC/DST, MCP_SRC/DST,
HAS_PLUGINS; conditional install_plugins; conditional install_settings;
framework-aware vault-setup check; framework-neutral summary messages.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Fix adapters to follow the same template.

fix: restore adapter_build() contract, revert function renames

Both adapters now export adapter_build() and adapter_translate_*() as
the uniform public contract. scripts/build.sh sources one adapter and
calls adapter_build uniformly. Private helpers (_oc_*) and vocabulary
tables (cc_capability_to_tools, oc_capability_to_permission, etc.)
retain their prefixes. CC regression and OC unit tests all pass.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

fix(tests): restore test_oc_ prefix on adapter_build end-to-end test

* Fix agent format in opencode adapter

* refactor: rename --framework to --platform across all scripts and tests

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Modify generic name for model tiers

Co-Authored-By: win0na <winnie@winneon.moe>

refactor: neutral model vocabulary (low/mid/high) in source agents

feat(claude-code): cc_model_to_native() maps low/mid/high to haiku/sonnet/opus

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

feat(opencode): update oc_model_to_provider() for low/mid/high vocabulary

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Add gemini-cli adapter

Co-Authored-By: win0na <winnie@winneon.moe>

build(gemini-cli): adapter skeleton with capability/event/model tables

build(gemini-cli): adapter_translate_dispatcher (DISPATCHER.md → GEMINI.md)

build(gemini-cli): adapter_translate_references and adapter_translate_skills

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

build(gemini-cli): adapter_translate_agents with capability→tools mapping

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

build(gemini-cli): adapter_translate_hooks with wrapper scripts

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

feat(install): add gemini-cli platform to launchme.sh and updateme.sh

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Implement preserving config merge for opencode.

Co-Authored-By: win0na <winnie@winneon.moe>

feat(opencode): config-merge.sh with formatting-preserving JSON merge

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

build(opencode): source config-merge.sh from adapter

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

feat(install): use oc_config_merge for opencode.json instead of overwrite

Source config-merge.sh from install scripts for opencode platform so
user keys in opencode.json are preserved on reinstall and update.
Fix in-place merge by writing to a temp file before moving to output.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Add mcp files to gitignore.

* Fix claude-specific references in agents, skills and references

* Fix: remove claude-specific reference from hooks.

build: add platform_dir and dispatcher_name to all hook wrapper/plugin templates

feat(hooks): platform-aware path checks using platform_dir and dispatcher_name from JSON input

test: update regression snapshot for platform-aware hook wrappers and scripts

* Added interactive platform choice in launchme, and platform auto-detection in updateme.

* Fix: remove claude-specific references from documentation

* Update documentation to reflect the new platform-agnostic architecture

* fix: address Copilot review feedback on PR #32

- tests/run.sh: check source return code, report failures
- tests/regression/run.sh: use mktemp + trap cleanup instead of fixed /tmp paths
- tests/regression/run.sh: include .mcp.json in regression comparison
- tests/regression/take-snapshot.sh: use --platform flag instead of stale scripted input
- adapters/opencode/templates/plugin-stub.js.tmpl: include stdout in hook block error message

* fix: address Copilot review round 2

- config-merge.sh: reword comment to only promise indentation preservation (not full formatting)
- take-snapshot.sh: copy required artifacts explicitly, optional ones with existence check
- adapters/lib.sh: document parse_hook_yaml single-trigger limitation

* fix: address Copilot review round 3

- adapters/opencode/adapter.sh: replace python3 template substitution with
  pure bash (while-read loop with case matching), removing python3 dependency
- adapters/lib.sh: should_include now falls back to plain YAML key read for
  files without frontmatter delimiters (fixes hook .yaml exclude: support)

* fix: address Copilot review round 4

- scripts/launchme.sh: fix double-dot in FW_DIR_NAME display (basename
  already includes the dot, e.g. ".claude")
- scripts/launchme.sh: replace undefined MCP_ANSWER with check on MCP_DST
  existence for summary banner

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-10 23:28:28 +02:00

7.2 KiB
Executable File

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