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>/:
| Artifact |
File |
When |
| TaskIntentDraft |
10-intent.md and optional task-intent-draft.json |
Start protocol |
| BaselineReadSetHint |
10-intent.md (inline) |
Start protocol |
| BaselineUsageDraft |
10-intent.md (inline) and optional baseline-usage-draft.json |
Start protocol and when baseline usage changes |
| ImpactStatementDraft |
10-intent.md (inline) |
Start protocol |
| TodoCheckpointDraft |
20-checkpoint.md and optional todo-checkpoint-draft.json |
Each checkpoint |
| ResumeStateHint |
20-checkpoint.md (inline) |
Each pause/handoff |
| DriftCheckDraft |
20-checkpoint.md (inline) and optional drift-check-draft.json |
Per-slice protocol |
| EvidenceBundleDraft |
90-evidence.md and optional evidence-bundle-draft.json |
Per-slice protocol |
| Reflection |
99-reflection.md |
Completion candidate |
For medium+ complexity tasks only. Low-complexity tasks skip work/.
Planless Slice Lane:
Use this lane when a parent plan or parent spec already owns the long-task
workstream and the current micro-slice only executes or refines one bounded
parent task.
Record a compact Slice Card instead of creating another durable plan/spec:
Slice Card:
- Goal:
- Parent plan/spec:
- Files:
- Boundary:
- Verification:
- Stop:
Slice Card Goal anchors slice-level completeness only.
It does not by itself grant whole-task completion.
Final completion still requires verification-before-completion Goal Closure
against the parent plan/spec and any active goal frame.
Do not create new plan/spec files for micro-slices that stay inside the
parent plan, existing compatibility boundary, and known verification path.
Update the existing checkpoint, evidence, and drift records when persistent
state is needed.
Escalate out of this lane only when a new owner, contract, schema, public API,
architecture boundary, migration, persistence, security/permission,
distribution/release surface, or unclear verification boundary appears.
When durable architecture decisions are in scope, these work records are the
preferred ADR Auto Backfill source. Preserve ADR signals, source refs,
alternatives, compatibility boundaries, drift checks, retirement notes, and
baseline-sync questions in the work record instead of relying on memory at
completion time.
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:
Initialize before writing work records:
python <aegis-workspace-helper> init --root <target-project-root>
For a new medium+ task process trail, prefer helper-backed lifecycle
creation over hand-created files:
python <aegis-workspace-helper> new-work --root <target-project-root> --date YYYY-MM-DD --slug <slug> --title "<title>" --requested-outcome "<outcome>" --scope "<scope>" --change-kind <kind>
After each slice, update checkpoint, evidence, and drift through the helper:
python <aegis-workspace-helper> add-checkpoint --root <target-project-root> --work YYYY-MM-DD-<slug> ...
python <aegis-workspace-helper> add-baseline-usage --root <target-project-root> --work YYYY-MM-DD-<slug> ...
python <aegis-workspace-helper> add-evidence --root <target-project-root> --work YYYY-MM-DD-<slug> ...
python <aegis-workspace-helper> add-drift-check --root <target-project-root> --work YYYY-MM-DD-<slug> ...
Before pause, handoff, or completion candidate, assemble a structural proof
bundle and check the workspace:
python <aegis-workspace-helper> bundle --root <target-project-root> --work YYYY-MM-DD-<slug>
python <aegis-workspace-helper> 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:
- State the requested outcome, scope, non-goals, and risk hints.
- If goal framing exists, restate goal, success evidence, stop condition, and
non-goals. Stop condition must allow done, blocked, needs-verification, and
scope-exceeded outcomes.
- Identify baseline refs that must be read before changing files.
- Record baseline usage state:
- required baseline refs
- optionally delivered context refs when the host can project them
- acknowledged before plan refs
- cited in plan refs
- missing refs
- Create or update the todo map.
- Create the first checkpoint:
- current todo
- active slice
- completed todos
- evidence refs
- blocked-on items
- next step
- If baseline refs are missing, pause in
needs-baseline-readback.
- 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:
- current goal
- current todo
- intended edits
- explicit non-edits
- verification command or manual check
For micro-slices under an existing parent plan, use the Planless Slice Lane and
state the Slice Card instead of opening a new planning/specification artifact.
After each work slice, update:
- completed todos
- evidence refs
- baseline usage if newly required refs were acknowledged, cited, or found missing
- blockers
- next step
- drift check
- helper-backed JSON sidecars through
aegis-workspace.py add-checkpoint,
aegis-workspace.py add-baseline-usage, 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:
- Read latest checkpoint.
- Read latest resume hint if present.
- Re-read original task intent.
- Re-read required baseline refs.
- Compare current worktree state with checkpoint claims.
- 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?
- Does the current work still serve the goal and stop condition?
- 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:
- Use aegis:verification-before-completion.
- Confirm every todo has a status.
- Confirm blockers are resolved or externalized.
- Confirm evidence refs cover the acceptance criteria.
- Confirm drift check has no blocking state.
- Run
python <aegis-workspace-helper> bundle --root <target-project-root> --work YYYY-MM-DD-<slug> if the helper is available and a work record
exists.
- Run
python <aegis-workspace-helper> check --root <target-project-root>
if the helper is available and the task wrote docs/aegis/ records.
- Treat the generated
GateInputPack as future-runtime input only.
- If durable architecture decisions were in scope, pass the work record,
proof bundle, drift checks, evidence refs, and ADR signals into
aegis:verification-before-completion for ADR Backfill Check.
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
BaselineUsageDraft: required refs, acknowledged refs, cited refs, missing refs, decision
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
1---2name: long-task-continuation3description: Use when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion.4metadata:5 source: https://skillmd.com/skills/concertonotes/long-task-continuation6---78# Long Task Continuation910## Overview1112Use this skill to keep long tasks checkpointed, resumable, drift-aware, and evidence-gated.1314This is a protocol skill. It does not execute plans, dispatch subagents, run tests, or grant completion authority.1516## Authority Boundary1718Current owner:1920- Method Pack protocol discipline2122Not owned here:2324- plan execution25- subagent dispatch26- host daemon / watchdog / automatic retry27- authoritative `GateDecision`28- evidence sufficiency final judgment29- completion authority3031## When To Use3233Use this skill when any of these are true:3435- the task has multiple phases or more than one meaningful work slice36- the task may be interrupted, compacted, resumed, or handed off37- the task uses subagents38- the user explicitly asks for long-task continuity, resume safety, or avoiding drift39- the task changes architecture, contracts, shared workflows, or verification gates4041For short direct answers or one-command checks, do not force this protocol.4243## Required Artifacts4445Maintain artifacts under `docs/aegis/work/YYYY-MM-DD-<slug>/`:4647| Artifact | File | When |48|----------|------|------|49| TaskIntentDraft | `10-intent.md` and optional `task-intent-draft.json` | Start protocol |50| BaselineReadSetHint | `10-intent.md` (inline) | Start protocol |51| BaselineUsageDraft | `10-intent.md` (inline) and optional `baseline-usage-draft.json` | Start protocol and when baseline usage changes |52| ImpactStatementDraft | `10-intent.md` (inline) | Start protocol |53| TodoCheckpointDraft | `20-checkpoint.md` and optional `todo-checkpoint-draft.json` | Each checkpoint |54| ResumeStateHint | `20-checkpoint.md` (inline) | Each pause/handoff |55| DriftCheckDraft | `20-checkpoint.md` (inline) and optional `drift-check-draft.json` | Per-slice protocol |56| EvidenceBundleDraft | `90-evidence.md` and optional `evidence-bundle-draft.json` | Per-slice protocol |57| Reflection | `99-reflection.md` | Completion candidate |5859For medium+ complexity tasks only. Low-complexity tasks skip work/.6061Planless Slice Lane:6263- Use this lane when a parent plan or parent spec already owns the long-task64 workstream and the current micro-slice only executes or refines one bounded65 parent task.66- Record a compact Slice Card instead of creating another durable plan/spec:6768 ```text69 Slice Card:70 - Goal:71 - Parent plan/spec:72 - Files:73 - Boundary:74 - Verification:75 - Stop:76 ```7778- Slice Card `Goal` anchors slice-level completeness only.79- It does not by itself grant whole-task completion.80- Final completion still requires `verification-before-completion` Goal Closure81 against the parent plan/spec and any active goal frame.8283- Do not create new plan/spec files for micro-slices that stay inside the84 parent plan, existing compatibility boundary, and known verification path.85- Update the existing checkpoint, evidence, and drift records when persistent86 state is needed.87- Escalate out of this lane only when a new owner, contract, schema, public API,88 architecture boundary, migration, persistence, security/permission,89 distribution/release surface, or unclear verification boundary appears.9091When durable architecture decisions are in scope, these work records are the92preferred ADR Auto Backfill source. Preserve ADR signals, source refs,93alternatives, compatibility boundaries, drift checks, retirement notes, and94baseline-sync questions in the work record instead of relying on memory at95completion time.9697These are draft / hint / projection inputs. They are not authoritative runtime records.9899## Workspace Helper Protocol100101When configured Aegis workspace support or installed Aegis workspace support is102available, use it for the target project workspace and lifecycle records:1031041. Initialize before writing work records:105106 ```bash107 python <aegis-workspace-helper> init --root <target-project-root>108 ```1091102. For a new medium+ task process trail, prefer helper-backed lifecycle111 creation over hand-created files:112113 ```bash114 python <aegis-workspace-helper> new-work --root <target-project-root> --date YYYY-MM-DD --slug <slug> --title "<title>" --requested-outcome "<outcome>" --scope "<scope>" --change-kind <kind>115 ```1161173. After each slice, update checkpoint, evidence, and drift through the helper:118119 ```bash120 python <aegis-workspace-helper> add-checkpoint --root <target-project-root> --work YYYY-MM-DD-<slug> ...121 python <aegis-workspace-helper> add-baseline-usage --root <target-project-root> --work YYYY-MM-DD-<slug> ...122 python <aegis-workspace-helper> add-evidence --root <target-project-root> --work YYYY-MM-DD-<slug> ...123 python <aegis-workspace-helper> add-drift-check --root <target-project-root> --work YYYY-MM-DD-<slug> ...124 ```1251264. Before pause, handoff, or completion candidate, assemble a structural proof127 bundle and check the workspace:128129 ```bash130 python <aegis-workspace-helper> bundle --root <target-project-root> --work YYYY-MM-DD-<slug>131 python <aegis-workspace-helper> check --root <target-project-root>132 ```133134These helper checks validate workspace structure, index coverage, and JSON135sidecar shape only. They do not determine evidence sufficiency, do not produce136authoritative `GateDecision`, and do not grant completion authority.137138## Start Protocol139140Before long-task execution:1411421. State the requested outcome, scope, non-goals, and risk hints.1432. If goal framing exists, restate goal, success evidence, stop condition, and144 non-goals. Stop condition must allow done, blocked, needs-verification, and145 scope-exceeded outcomes.1463. Identify baseline refs that must be read before changing files.1474. Record baseline usage state:148 - required baseline refs149 - optionally delivered context refs when the host can project them150 - acknowledged before plan refs151 - cited in plan refs152 - missing refs1535. Create or update the todo map.1546. Create the first checkpoint:155 - current todo156 - active slice157 - completed todos158 - evidence refs159 - blocked-on items160 - next step1617. If baseline refs are missing, pause in `needs-baseline-readback`.1628. If the workspace helper is available, use `aegis-workspace.py new-work` to163 create/index the first `docs/aegis/work/` files and run `check --root164 <target-project-root>` before continuing.165166## Per-Slice Protocol167168Before each work slice, restate:1691701. current goal1712. current todo1723. intended edits1734. explicit non-edits1745. verification command or manual check175176For micro-slices under an existing parent plan, use the Planless Slice Lane and177state the Slice Card instead of opening a new planning/specification artifact.178179After each work slice, update:1801811. completed todos1822. evidence refs1833. baseline usage if newly required refs were acknowledged, cited, or found missing1844. blockers1855. next step1866. drift check1877. helper-backed JSON sidecars through `aegis-workspace.py add-checkpoint`,188 `aegis-workspace.py add-baseline-usage`, `aegis-workspace.py add-evidence`, and `aegis-workspace.py add-drift-check`189 when available190191If no fresh evidence exists, the state is `needs-verification` or `partial`.192193## Resume Protocol194195When resuming:1961971. Read latest checkpoint.1982. Read latest resume hint if present.1993. Re-read original task intent.2004. Re-read required baseline refs.2015. Compare current worktree state with checkpoint claims.2026. If checkpoint, baseline, and worktree disagree, pause and ask for direction.203204Never resume from memory alone.205206## Drift Check207208Answer these after each slice:209210- Does the current work still serve the original task intent?211- Does the current work still serve the goal and stop condition?212- Did the slice stay inside the compatibility boundary?213- Did any new owner, fallback, adapter, or branch appear?214- Is the retirement track still explicit?215- Did the evidence bundle grow enough to support the next claim?216217Allowed decisions:218219- `continue`220- `pause-for-user`221- `needs-baseline-readback`222- `needs-verification`223- `blocked`224225Forbidden decisions:226227- `gate-passed`228- `completion-granted`229- `authoritatively-safe`230231## Completion Candidate Protocol232233Before saying work is complete:2342351. Use aegis:verification-before-completion.2362. Confirm every todo has a status.2373. Confirm blockers are resolved or externalized.2384. Confirm evidence refs cover the acceptance criteria.2395. Confirm drift check has no blocking state.2406. Run `python <aegis-workspace-helper> bundle --root <target-project-root>241 --work YYYY-MM-DD-<slug>` if the helper is available and a work record242 exists.2437. Run `python <aegis-workspace-helper> check --root <target-project-root>`244 if the helper is available and the task wrote `docs/aegis/` records.2458. Treat the generated `GateInputPack` as future-runtime input only.2469. If durable architecture decisions were in scope, pass the work record,247 proof bundle, drift checks, evidence refs, and ADR signals into248 aegis:verification-before-completion for ADR Backfill Check.249250Method Pack output is verified evidence and advisory judgment only. It is not authoritative completion.251252## Minimal Reporting Shape253254Use this shape for long-task updates:255256- `TodoCheckpointDraft`: current todo, completed todos, active slice, next step257- `BaselineUsageDraft`: required refs, acknowledged refs, cited refs, missing refs, decision258- `Evidence`: commands, files, logs, or manual checks259- `DriftCheckDraft`: scope, compatibility, retirement, decision260- `Risk / Unknown`: unresolved blockers or missing evidence261- `Next`: the next smallest safe action