Long Task Continuation

Long Task Continuation

Overview

Use this skill to keep long tasks checkpointed, resumable, drift-aware, and evidence-gated.

This is a protocol skill. It does not execute plans, dispatch subagents, run tests, or grant completion authority.

Authority Boundary

Current owner:

• Method Pack protocol discipline

Not owned here:

• plan execution
• subagent dispatch
• host daemon / watchdog / automatic retry
• authoritative GateDecision
• evidence sufficiency final judgment
• completion authority

When To Use

Use this skill when any of these are true:

• the task has multiple phases or more than one meaningful work slice
• the task may be interrupted, compacted, resumed, or handed off
• the task uses subagents
• the user explicitly asks for long-task continuity, resume safety, or avoiding drift
• the task changes architecture, contracts, shared workflows, or verification gates

For short direct answers or one-command checks, do not force this protocol.

Required Artifacts

Maintain artifacts under docs/aegis/work/YYYY-MM-DD-<slug>/:

For medium+ complexity tasks only. Low-complexity tasks skip work/.

These are draft / hint / projection inputs. They are not authoritative runtime records.

Workspace Helper Protocol

When configured Aegis workspace support or installed Aegis workspace support is available, use it for the target project workspace and lifecycle records:

1. Initialize before writing work records:

   python scripts/aegis-workspace.py init --root <target-project-root>
   

2. For a new medium+ task process trail, prefer helper-backed lifecycle creation over hand-created files:

   python scripts/aegis-workspace.py new-work --root <target-project-root> --date YYYY-MM-DD --slug <slug> --title "<title>" --requested-outcome "<outcome>" --scope "<scope>" --change-kind <kind>
   

3. After each slice, update checkpoint, evidence, and drift through the helper:

   python scripts/aegis-workspace.py add-checkpoint --root <target-project-root> --work YYYY-MM-DD-<slug> ...
   python scripts/aegis-workspace.py add-evidence --root <target-project-root> --work YYYY-MM-DD-<slug> ...
   python scripts/aegis-workspace.py add-drift-check --root <target-project-root> --work YYYY-MM-DD-<slug> ...
   

4. Before pause, handoff, or completion candidate, assemble a structural proof bundle and check the workspace:

   python scripts/aegis-workspace.py bundle --root <target-project-root> --work YYYY-MM-DD-<slug>
   python scripts/aegis-workspace.py check --root <target-project-root>
   

These helper checks validate workspace structure, index coverage, and JSON sidecar shape only. They do not determine evidence sufficiency, do not produce authoritative GateDecision, and do not grant completion authority.

Start Protocol

Before long-task execution:

1. State the requested outcome, scope, non-goals, and risk hints.
2. Identify baseline refs that must be read before changing files.
3. Create or update the todo map.
4. Create the first checkpoint:
   • current todo
   • active slice
   • completed todos
   • evidence refs
   • blocked-on items
   • next step
5. If baseline refs are missing, pause in needs-baseline-readback.
6. If the workspace helper is available, use aegis-workspace.py new-work to create/index the first docs/aegis/work/ files and run check --root <target-project-root> before continuing.

Per-Slice Protocol

Before each work slice, restate:

1. current goal
2. current todo
3. intended edits
4. explicit non-edits
5. verification command or manual check

After each work slice, update:

1. completed todos
2. evidence refs
3. blockers
4. next step
5. drift check
6. helper-backed JSON sidecars through aegis-workspace.py add-checkpoint, aegis-workspace.py add-evidence, and aegis-workspace.py add-drift-check when available

If no fresh evidence exists, the state is needs-verification or partial.

Resume Protocol

When resuming:

1. Read latest checkpoint.
2. Read latest resume hint if present.
3. Re-read original task intent.
4. Re-read required baseline refs.
5. Compare current worktree state with checkpoint claims.
6. If checkpoint, baseline, and worktree disagree, pause and ask for direction.

Never resume from memory alone.

Drift Check

Answer these after each slice:

• Does the current work still serve the original task intent?
• Did the slice stay inside the compatibility boundary?
• Did any new owner, fallback, adapter, or branch appear?
• Is the retirement track still explicit?
• Did the evidence bundle grow enough to support the next claim?

Allowed decisions:

• continue
• pause-for-user
• needs-baseline-readback
• needs-verification
• blocked

Forbidden decisions:

• gate-passed
• completion-granted
• authoritatively-safe

Completion Candidate Protocol

Before saying work is complete:

1. Use aegis:verification-before-completion.
2. Confirm every todo has a status.
3. Confirm blockers are resolved or externalized.
4. Confirm evidence refs cover the acceptance criteria.
5. Confirm drift check has no blocking state.
6. Run python scripts/aegis-workspace.py bundle --root <target-project-root> --work YYYY-MM-DD-<slug> if the helper is available and a work record exists.
7. Run python scripts/aegis-workspace.py check --root <target-project-root> if the helper is available and the task wrote docs/aegis/ records.
8. Treat the generated GateInputPack as future-runtime input only.

Method Pack output is verified evidence and advisory judgment only. It is not authoritative completion.

Minimal Reporting Shape

Use this shape for long-task updates:

• TodoCheckpointDraft: current todo, completed todos, active slice, next step
• Evidence: commands, files, logs, or manual checks
• DriftCheckDraft: scope, compatibility, retirement, decision
• Risk / Unknown: unresolved blockers or missing evidence
• Next: the next smallest safe action