scbe-github-sweep-sorter
Sort GitHub and local repo sweeps into governed agent lanes using HYDRA formations, roundtable role assignments, repo triage buckets, and deterministic handoff packets. Use when classifying repos, PRs, issues, security alerts, or dirty trees before assigning collaborative AI work in one shared codebase.
Best use case
scbe-github-sweep-sorter is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Sort GitHub and local repo sweeps into governed agent lanes using HYDRA formations, roundtable role assignments, repo triage buckets, and deterministic handoff packets. Use when classifying repos, PRs, issues, security alerts, or dirty trees before assigning collaborative AI work in one shared codebase.
Teams using scbe-github-sweep-sorter should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/scbe-github-sweep-sorter/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How scbe-github-sweep-sorter Compares
| Feature / Agent | scbe-github-sweep-sorter | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Sort GitHub and local repo sweeps into governed agent lanes using HYDRA formations, roundtable role assignments, repo triage buckets, and deterministic handoff packets. Use when classifying repos, PRs, issues, security alerts, or dirty trees before assigning collaborative AI work in one shared codebase.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# SCBE GitHub Sweep Sorter
Use this skill when a repo or org needs to be swept, sorted, and routed into explicit agent lanes before coding starts.
Pair this skill with:
- `scbe-ai-to-ai-communication` for packet delivery and handoff logging
- `multi-agent-orchestrator` when the sweep turns into parallel execution
## Quick Start
1. Collect the sweep surface.
- Local: `git status`, repo hygiene reports, branch state, changed roots.
- GitHub: PRs, issues, alerts, repo inventory, review queues.
2. Bucket items before fixing anything.
- `keep-in-repo`
- `archive-or-cloud`
- `ignore-or-cache`
- `security-now`
- `manual-review`
3. Choose a HYDRA formation with `scripts/choose_formation.py`.
4. Build one roundtable packet with `scripts/build_roundtable_packet.py`.
5. Hand the packet to the communication lane instead of letting agents collide.
## Formation Selection
Read `references/formations.md` when the right formation is not obvious.
Default formation rules:
- `scatter`
- Use for discovery across many repos, many alerts, or broad org triage.
- Best when the work is mostly classification and evidence gathering.
- `hexagonal-ring`
- Default coding and repo-governance formation for the six Sacred Tongues.
- Best when multiple agents collaborate on one shared codebase but ownership stays explicit.
- `tetrahedral`
- Use for smaller, high-focus, higher-risk implementation packets.
- Best when four critical roles are enough and shared-file pressure is high.
- `ring`
- Use when order matters.
- Best for approvals, critical security actions, release gates, and chain-of-custody decisions.
## Role Map
Read `references/role-map.md` for the full mapping.
Default six-tongue roundtable:
- `KO` architecture curator
- `AV` transport and discovery
- `RU` policy and governance
- `CA` implementation engineer
- `UM` security auditor
- `DR` schema, release memory, and evidence keeper
Optional spine role:
- `SPINE` integration coordinator
- owns packet routing, status rollup, and conflict resolution
- does not compete with the six tongues for the same file edits
## Governance Thresholds
Read `references/governance-thresholds.md` when deciding quorum.
Use risk-tiered thresholds, not one fixed quorum claim:
- low-risk classification and discovery: `3/6`
- medium-risk code or config changes: `4/6`
- critical security, destructive, or release actions: `5/6`
- ordered attestation path required: use `ring` and preserve signer order
Use the corrected language:
- prefer `BFT-informed threshold governance`
- do not claim a single hard Byzantine quorum for every action
## Sweep Workflow
### 1. Collect
Gather only what the sweep needs:
- repo name and branch
- dirty-tree summary
- PR / issue / alert counts
- high-risk roots or files
- whether the task is discovery, implementation, review, or release
### 2. Classify
Use `scripts/classify_sweep_targets.py` for a first pass.
The target buckets are:
- `keep-in-repo`
- `archive-or-cloud`
- `ignore-or-cache`
- `security-now`
- `manual-review`
The purpose is not deletion. The purpose is separating source, evidence, outputs, and cache so the repo stays readable.
### 3. Choose Formation
Use `scripts/choose_formation.py` to pick:
- formation
- quorum target
- whether ordering is required
- whether a shared-file collision risk exists
### 4. Assign Work
Every packet must declare:
- `task_id`
- `formation`
- `quorum_required`
- `owner_role`
- `allowed_paths`
- `blocked_paths`
- `goal`
- `done_criteria`
Never let two agents edit the same mutable file without explicit ownership.
### 5. Emit Packet
Use `scripts/build_roundtable_packet.py` to create a machine-readable packet.
If the work will be handed to another AI, route the packet through `scbe-ai-to-ai-communication`.
## Output Contract
Read `references/packet-schema.md` for the full packet.
Minimum output:
```json
{
"task_id": "sweep-20260314-001",
"repo": "SCBE-AETHERMOORE",
"branch": "main",
"formation": "hexagonal-ring",
"quorum_required": "4/6",
"summary": "Sort security alerts and repo hygiene roots into owned lanes",
"work_packets": [
{
"tongue": "KO",
"role": "architecture-curator",
"goal": "Confirm boundaries and non-goals",
"allowed_paths": ["docs/", "schemas/"],
"blocked_paths": ["src/", "tests/"]
}
]
}
```
## Safety Rules
- Keep one shared mission, not one shared file free-for-all.
- Preserve evidence and artifacts; sort them before deciding whether they belong in repo or archive.
- For critical actions, preserve ordered roundtable signatures.
- Treat `Word`, `browser`, `workflow`, and `repo` clients as outer execution planes. The sweep packet governs them; it does not get replaced by them.
- Do not confuse cache outputs with successful workflow templates.
## References
- `references/formations.md`
- `references/role-map.md`
- `references/governance-thresholds.md`
- `references/packet-schema.md`
## Scripts
- `scripts/choose_formation.py`
- `scripts/classify_sweep_targets.py`
- `scripts/build_roundtable_packet.py`Related Skills
scbe-training-pair-authoring
Create prompt and response and metadata training pairs from SCBE documents, repair traces, terminal sessions, and operational workflows using the repository's canonical dataset contract and provenance rules.
scbe-spin-conversation-engine
Generate SFT training data via radial matrix conversation pivots with D&D-style combat research mode. Produces diverse, cost-effective training pairs with Sacred Tongue encoding, golden spiral problem distribution, and harmonic re-attunement.
scbe-research-training-bridge
Stage arXiv evidence and Obsidian markdown into source-grounded Hugging Face training bundles for research, review, and later SFT runs.
scbe-document-management
Consolidate overlapping docs, classify files by authority, and keep SCBE repo documents aligned with runtime truth. Use when the repo has drift between canonical docs, public docs, proposal notes, research branches, and generated evidence.
scbe-colab-bridge
Control Google Colab notebooks from Claude Code via Chrome extension. Execute cells, run terminal commands, read outputs, and manage GPU compute remotely.
scbe-claim-to-code-evidence
Map SCBE Notion technical claims, proof pages, and patent-facing architecture notes to concrete repository evidence such as code paths, tests, demos, and docs. Use when Codex needs to build a due-diligence packet, claim-to-code audit, implementation crosswalk, patent support note, or proof summary from local Notion exports and repo artifacts.
scbe-autonomous-worker-productizer
Turn SCBE automation, autonomous worker, and revenue-system notes into concrete offers, workflow packs, pilot plans, or SaaS-facing product packets. Use when Codex needs to package Notion automation pages into buyer-ready offerings, n8n/Zapier workflow designs, flock-backed worker systems, or implementation roadmaps tied to existing SCBE repo surfaces.
scbe-code-scanning-ops
Operate GitHub code scanning and CodeQL remediation for SCBE repositories. Use when triaging code-scanning alerts, mapping alert classes to fix patterns, validating targeted regressions, or wiring dedicated CodeQL workflows and runbooks into the repo.
scbe-world-anvil-lore-rag-7th-tongue
Build and operate a lore-focused RAG system using World Anvil exports and SCBE docs, with deterministic Claude/Codex cross-talk packets for handoff. Use when users ask to structure lore canon retrieval, sync worldbuilding data, enforce citation-grounded generation, or coordinate a 7th Tongue overseer lane across multiple AI agents.
scbe-webtoon-book-conversion
Convert The Six Tongues Protocol and related manuscript sections into webtoon/manhwa storyboard packets, episode roadmaps, panel expansion plans, and image-generation-ready prompt lanes. Use when extending the series storyboard, adapting book chapters into vertical scroll episodes, or keeping art generation tied to canon instead of drifting into generic fantasy panels.
scbe-voice-render-verification
Govern and verify SCBE voice rendering work that maps Langues weighting into breath, phase, and Layer 14 audio-axis packets. Use when implementing or reviewing `scripts/voice_gen_hf.py`, emitting sidecar voice packets, validating canonical tongue ordering, tuning breath planning or phase timing, or keeping voice docs and code aligned with `docs/LANGUES_WEIGHTING_SYSTEM.md` and `docs/specs/SCBE_VOICE_EMOTIONAL_TIMBRE_SYSTEM.md`.
scbe-universal-synthesis
Orchestrate all installed Codex skills through an auto-updating synthesis matrix with Sacred Tongues routing, emotion/intent metadata, and decodable lexicon packets tied to established SCBE characters. Use when the user asks for cross-skill coordination, auto skill updates, multi-skill routing, or Sacred Tongues intent mapping.