Start Session

start-session

The always-on entry point for an atlas session. Assemble the Session Primer, hold it as starting context, then route to the right skill.

These thoughts mean STOP — you are rationalizing:

Building the Session Primer first is not optional. The one exception is the quiet exit in §1: if the primer reports the project is not an atlas workspace, stop silently and proceed normally — do not pitch initialization.

1. Build the Session Primer

Run the bundled build_primer.py relative to this skill directory. Take the source path the harness supplied for the currently loaded SKILL.md, resolve its sibling build_primer.py, verify that file exists, then invoke its absolute path with unqualified python3 so the active shell PATH selects the interpreter.

If the harness did not expose the loaded skill's source path, or the sibling script is missing, stop and report start-session cannot locate its bundled build_primer.py. Do not search known install roots or fall back to another copy.

• If it prints ATLAS_UNINITIALIZED: …, this project has no Project Binding (.atlas.toml) — it isn't an atlas workspace. Stop silently and proceed with the user's request normally; do not mention atlas or pitch initialization. This skill triggers on any session (the trigger lives in the skill, not in a per-project file), so an unbound project is the common, expected case — exit quietly. Only route to initialize-atlas if the user is explicitly setting up atlas (e.g. "initialize my workspace", "bind this repo to a vault").
• If it reports ATLAS_PATH is not set, the vault location is unknown — ask the user to export ATLAS_PATH=<their atlas vault root> (it always points at the atlas vault), then re-run.
• Otherwise, treat the printed payload as your Active Context for the session — User Profile, Shared Memory, the Workspace Brief, and (when bound) mimir overview. Internalize it; don't echo it back to the user.
• In a Mimir-bound repo, explicitly load the mimir skill now for its routing and lifecycle contract. The overview already present in the Primer satisfies that skill's orientation gate; do not query it again.
• If the payload opens with a ⚠️ Consolidation due banner, hold its recommendation until the current Session reaches a boundary. Do not interrupt Session Start; at the boundary, recommend consolidate-workspace.

2. Present a work slate for an open-ended start

In a Mimir-bound workspace, a conversational opening that contains no concrete directive is an invitation to orient the user with a small, decision-ready work slate. This is an intent rule, not a phrase list: a greeting, "what's next?", or a similar open-ended start qualifies. If the user already named the work they want, follow that directive instead — never interrupt it with a queue report. Without a primer-composed Mimir overview, respond conversationally and do not invent a work slate or seek another queue authority.

Build the slate from the Mimir orientation already present in the Session Primer:

1. Resume before redirecting. If work is in flight, recommend resuming it and explain its current state. Alternatives may remain visible, but make clear that choosing one means switching away from active work.
2. Otherwise select, don't dump. Choose from the ready candidates in the overview using queue order, project and container direction, dependency-unblocking value, urgency, hygiene, and size. Rank is an input, not a substitute for judgment.
3. Offer up to three credible choices. Lead with Recommended, then add a strategically meaningful Alternative and a genuine Quick win when the queue supports those roles. Do not manufacture options or force a third choice.
4. Use bounded drill-down. Start with the candidates already in mimir overview. Read an individual task only when the overview lacks enough context to describe a selected option truthfully. A conversational start is not a full-board grooming pass.
5. Make every option decision-ready. Usually give each choice a short paragraph of two or three sentences: what outcome it produces, why it matters now, any material dependency, risk, or stale-state caveat, and its approximate size when known. A task id and title alone are not an adequate description.
6. Keep hygiene distinct. Report relevant stale, blocked, or untriaged state in one compact Board attention note. Do not spend a work-choice slot on hygiene unless it materially changes the recommendation.

The recommendation should be clear, but the response remains an invitation to choose; do not start or mutate a task until the user selects the work.

3. Hold the through-line

A Session is bounded by a body of work, not by one context window. The primer is what you re-load on each resumption — including compactions, clears/resets, and new windows — to keep the work's through-line intact.

4. Decisions & glossary are live

The workspace glossary.md and decisions/ are authored by the domain-modeling skill: it maintains the glossary (from the project's context/domain terms) and writes the ADRs. Redirect that skill to the workspace location — the vault workspace (<ATLAS_PATH>/Workspaces/<workspace>/), where glossary.md and decisions/ live — rather than its default in-repo path.

Repo override: a repo may set decisions = "local" (or a path) in .atlas.toml to keep decisions/glossary in the repo instead of the vault workspace. When that key is present, honor the local target; otherwise default to the vault workspace.

Wherever they live, glossary.md and decisions/ are constraints on the work, not an archive — hold them open the whole session, whatever you're doing (planning, brainstorming, building):

• When planning, check the plan against decisions/. A conflict means either the plan is wrong or the decision is stale — resolve it before building; never silently violate a recorded norm. Updating a decision can cascade, so do it thoughtfully.
• Keep language true to glossary.md. Use its canonical terms and let them frame the problem; challenge drift the moment you notice it.
• Capture as it crystallizes — a term sharpens → glossary; a hard-to-reverse, surprising, real-trade-off decision → an ADR (offer ADRs sparingly). Route both through domain-modeling.

This is general practice, not gated behind any one skill.

5. Routing surface

From the Active Context and what the user wants, route to:

• initialize-atlas — bind/scaffold/heal the workspace (also when the primer reports uninitialized).
• mimir — own work-state routing and freeze task-anchored Session Summaries at meaningful boundaries.
• consolidate-workspace — lift a workspace's durable knowledge from pending Session Summaries into the workspace + Mimir.

6. Keep the vault high-signal

Follow resources/workspace-hygiene.md: keep the Brief durable and small, put new files in the right place, and let consolidation perform agent-authored Brief maintenance. Don't bloat Active Context. When writing any file into the vault, follow the frontmatter rules in resources/frontmatter.md so agents can find and progressively disclose it.