repo-manager/AGENTS.md

repo-manager — Agent Instructions

Repo Identity

Purpose: Repository representation, file-backed record indexing, reconciliation, governed repository control, and coach/lead/director agent roles for HelixForge.

Domain: infotech Repo slug: repo-manager Topic ID: cee7bedf-2b48-46ef-8601-006474f2ad7a Workplan prefix: RMGR-WP-

---

State Hub Integration

The Custodian State Hub tracks work across all domains. Codex uses HTTP REST and the statehub CLI by default. MCP is opt-in because the current Codex MCP bridge adds severe call latency; the full administrative MCP surface remains available to clients that need it.

Context	URL
Local workstation	http://127.0.0.1:8000
Remote (railiance01, in-cluster)	http://10.43.68.154:8000
Optional local edge relay	http://127.0.0.1:18080

Do not instruct a remote agent to use http://127.0.0.1:18000. That reverse tunnel is retired; on railiance01 reach the hub at the in-cluster address above.

When an operator has enabled the edge relay, set API_BASE to the relay URL. Queueable writes return an explicit queued receipt if the central hub is unreachable. Treat that as pending local evidence, then ask the operator to run statehub outbox status/replay after connectivity returns.

Codex workspace-write sandboxes need network access enabled to reach the host's loopback listener. Bootstrap this once with make -C ~/state-hub configure-codex and restart Codex. The canonical REST health endpoint is /state/health, not /health. If a sandboxed loopback probe fails, retry it with escalated execution before declaring State Hub unavailable; a managed Codex permission profile may still enforce isolated networking. Experimental MCP can be enabled explicitly with make -C ~/state-hub configure-codex WITH_MCP=1.

Orient at session start

# Offline brief — works without hub connection
cat .custodian-brief.md

# Active workplans for this domain
curl -s "http://127.0.0.1:8000/workplans/?topic_id=cee7bedf-2b48-46ef-8601-006474f2ad7a&status=active" \
  | python3 -m json.tool

# Check inbox
curl -s "http://127.0.0.1:8000/messages/?to_agent=repo-manager&unread_only=true" \
  | python3 -m json.tool

Mark a message read:

curl -s -X PATCH "http://127.0.0.1:8000/messages/<id>/read" \
  -H "Content-Type: application/json" -d '{}'

Log progress (required at session close)

curl -s -X POST http://127.0.0.1:8000/progress/ \
  -H "Content-Type: application/json" \
  -d '{
    "summary": "what was done",
    "event_type": "note",
    "author": "codex",
    "workplan_id": "<uuid>",
    "task_id": "<uuid>"
  }'

Omit workplan_id / task_id when not applicable.

Update task status

curl -s -X PATCH "http://127.0.0.1:8000/tasks/<task_id>" \
  -H "Content-Type: application/json" \
  -d '{"status": "progress"}'
# values: wait | todo | progress | done | cancel

Flag a task for human review

curl -s -X PATCH "http://127.0.0.1:8000/tasks/<task_id>" \
  -H "Content-Type: application/json" \
  -d '{"needs_human": true, "intervention_note": "reason"}'

---

Session Protocol

Start:

1. cat .custodian-brief.md — domain goal and open workplans (offline-safe)
2. Check inbox: GET /messages/?to_agent=repo-manager&unread_only=true; mark read
3. Scan workplans: ls workplans/ — note status: ready, active, or blocked files and open tasks
4. Check human-needed tasks: GET /tasks/?needs_human=true

During work:

• Update task statuses in workplan files as tasks progress
• Record significant decisions via POST /decisions/

Close:

1. Update workplan file task statuses to reflect progress
2. If finishing a workplan: hand off residuals as live work records first (intake with origin: residual + origin_ref: <WP-id>, or a next workplan / decision / engagement). Do not park leftovers only in prose or SCOPE.md. Canon: the-custodian/canon/standards/work-record-types_v0.1.md § Residuals.
3. Log: POST /progress/ with a summary of what changed (name handoff ids)
4. After workplan file changes, run:

   rmgr sync --path . --push
   

   The command assigns only missing deterministic identifiers, verifies the pushed Forgejo commit and primary/railiance01, then requests one central forge-derived reconciliation. A queued receipt is pending evidence; rerun after connectivity returns. Use statehub fix-consistency separately for a deep audit. registrar-reconcile is legacy migration/repair only.

---

Before requesting credentials or access, use warden route find "<need>" --json. Repo Manager never stores secret values in repository records, State Hub, workplans, logs, or chat.

Read INTENT.md, SCOPE.md, and history/2026-08-09-genesis.md before changing architectural boundaries. Repository files remain authoritative; database state is a replaceable projection. Observation and governed control belong to this component, while cross-entity messaging belongs to hub-core.

---

Workplan Convention (ADR-001)

Work items originate as files in this repo — not in the hub. The hub is a read/cache/index layer that rebuilds from files.

File location: workplans/RMGR-WP-NNNN-<slug>.md

Archived location: finished workplans may move to workplans/archived/YYMMDD-RMGR-WP-NNNN-<slug>.md. The YYMMDD prefix is the completion/archive date; the frontmatter id does not change.

Ad Hoc Tasks: small opportunistic fixes discovered during a session use workplans/ADHOC-YYYY-MM-DD.md with task ids ADHOC-YYYY-MM-DD-T01, etc. Use this only for low-risk work completed directly; create a normal workplan for anything needing analysis, design, approval, dependencies, or multiple phases.

Frontmatter:

---
id: RMGR-WP-NNNN
type: workplan
title: "..."
domain: infotech
repo: repo-manager
status: proposed | ready | active | blocked | backlog | finished | archived
owner: codex
topic_slug: ...
created: "YYYY-MM-DD"
updated: "YYYY-MM-DD"
state_hub_workstream_id: "<uuid>"   # deterministic UUIDv5; managed by Repo Manager
---

Use proposed for a new draft, ready after review against current repo state, and finished after implementation. stalled and needs_review are derived health labels, not frontmatter statuses.

Terminology: workplan is the fleet term; workstream appears only in legacy API/MCP/frontmatter bridges until STATE-WP-0069 retires them — see the-custodian/canon/standards/workplan-terminology-fleet_v0.1.md.

Task block format (one per ## section):

## Task Title

` ` `task
id: RMGR-WP-NNNN-T01
status: wait | todo | progress | done | cancel
priority: high | medium | low
state_hub_task_id: "<uuid>"         # deterministic UUIDv5; managed by Repo Manager
` ` `

Task description text.

Status progression: todo → progress → done; use wait for waiting/blocked work and cancel for stopped work.

Residuals when finishing: actionable leftovers become live work records before status: finished — usually an intake (origin: residual, origin_ref: RMGR-WP-NNNN) or a spawned workplan. Residual is a role, not a kind. Fleet list lives on State Hub, not in SCOPE.md.

To create a new workplan:

1. Write the file following the format above
2. Run rmgr sync --path . --push.
3. Run statehub fix-consistency only when a separate deep audit is needed.