- name
SKILL.md
Le fichier du skill reste dans le dépôt de l'éditeur.
Collez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add GanyuanRan/Aegis --skill long-task-continuation -a cursor -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add GanyuanRan/Aegis --skill long-task-continuation -a claude-code -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add GanyuanRan/Aegis --skill long-task-continuation -a codex -yCollez la commande copiée dans un terminal. Elle installe ce SKILL.md dans cet agent.
npx skills add GanyuanRan/Aegis --skill long-task-continuation -a grok -yEnvoyez le message copié dans un chat Grok Bot. Le Bot récupère ce SKILL.md sur GitHub et l'ajoute aux skills que partagent tous vos Bots.
Install this skill: https://github.com/GanyuanRan/Aegis/tree/HEAD/skills/long-task-continuationDe l'éditeur
Keep long work checkpointed, resumable, drift-aware, and evidence-gated. This protocol does not execute plans, dispatch subagents, run tests, or grant completion authority.
The Method Pack owns continuation discipline only. It does not own the parent
plan, host retry/watchdog behavior, authoritative GateDecision, evidence
sufficiency, requirement acceptance, or completion.
Use this skill when the work has meaningful phases, may be compacted/resumed or handed off, uses subagents, or explicitly needs continuity and drift control. Architecture, contract, shared-workflow, and verification-gate changes also benefit from it. Do not force it onto a short answer or one-command check.
Choose exactly one state carrier:
work/ record for
medium/high work, or for work of any complexity that actually crosses
sessions, needs handoff, or requires resumable state;Multi-step, todo-driven, possible-compaction, and subagent use do not force durable records for low-complexity work by themselves. Do not create both carriers or a record per slice.
A durable task has one process trail under
docs/aegis/work/YYYY-MM-DD-<slug>/. It keeps logical intent/baseline state,
the latest todo/checkpoint/resume state, terminal evidence/drift state, and a
completion reflection when warranted. These are
TaskIntentDraft, BaselineReadSetHint, BaselineUsageDraft,
ImpactStatementDraft, TodoCheckpointDraft, ResumeStateHint,
DriftCheckDraft, and EvidenceBundleDraft views—not authoritative runtime
records or separate plan owners.
Read only the lifecycle-matched section of durable-work-guidance.md:
## Required Artifact Layout and ## Create A Durable Work Record for a new durable work record;## Update A Slice when an existing helper-backed record needs sidecar updates;## Retry Convergence Detail for retry/attempt bookkeeping;## Pause, Handoff, And Completion Bundle when preparing a pause, handoff, or completion bundle; and## Expanded State Fields only when natural checkpoint prose is ambiguous.The reference owns artifact layout and <aegis-workspace-helper> command
detail; this file owns carrier selection, resume order, drift decisions, and
stop conditions.
An Execution Readiness View may be kept in the intent or active checkpoint
for medium/high, handoff-prone, long-running, subagent-driven, architecture,
contract, compatibility, or retirement-sensitive work. It renders existing
intent, scope, baseline, owner, test, review, and drift constraints; it is not a
new JSON artifact or completion authority.
Planless Slice Lane:
Slice Card: Goal, Parent plan/spec (or
none — direct bounded request), Files, Boundary, Verification, and Stop.verification-before-completion.When durable architecture decisions are in scope, these work records are the preferred ADR Auto Backfill source. Preserve decision signals, source refs, alternatives, compatibility, retirement, drift, and baseline-sync questions.
Before execution:
done | blocked | needs-verification | scope-exceeded).needs-baseline-readback.Execution Readiness View exists, retain its intent lock, scope
fence, baseline lock, compatibility/retirement boundary, tests, reviews,
evidence, and rewind rules.durable-work-guidance.md to create and
structurally check it before implementation.A failed verification is another attempt in the current slice, not a new
slice. Keep failed-attempt telemetry out of terminal evidence and normal
commits. Only evidence-finalized, blocked, or abandoned is terminal.
When retry state reaches process-artifact-pressure, stop auto-retry and route
to systematic-debugging or verification-before-completion. Load the durable
reference only when the attempt/evidence commands or sidecar rules are needed.
Before each slice, state the current goal/todo, intended edits, explicit non-edits, verification, and readiness alignment. A bounded parent-plan or no-parent slice uses the compact Slice Card rather than a new plan/spec.
After each slice, update completed todos, evidence refs, newly used baseline
refs, blockers, next step, and drift decision. When an active helper-backed work record exists, read durable-work-guidance.md and update that same record;
never create another workstream for bookkeeping.
When patch-shape/ripple triage, an H-class finding, or a bounded compatibility
mitigation fired, a locally green result does not clear the direction. Retain
PatchShape, CanonicalOwner, UpwardDrillSignal, latest outcome, and one
bounded evidence ref; do not copy raw logs or full diffs. If no fresh evidence
exists, the state is needs-verification or partial. For repairs or
optimization, retain the causal scope, evidence references, unresolved
influences that could change the solution, and verification coverage in the
same checkpoint. Compression must not turn one confirmed cause into a complete
root claim or erase counterevidence; recheck these unknowns before resuming
retained changes. Do not add a parallel causal record.
Resume in this order:
CONTEXT.md language.Execution Readiness View when present.needs-verification without forcing assent.
If evidence resolves it, retain the supported conclusion and verify normally.Any disagreement among plan, checkpoint, baseline, context, readiness view, or
worktree pauses execution. A semantic conflict routes to
establishing-project-context; an unplanned repair re-reads the retained
invariant, owner seam, patch shape, and causal topology, then route comparison to
systematic-debugging. A new carrier name alone does not prove a new direction. Never resume from memory alone.
Check original intent and stop condition, parent scope/acceptance, compatibility,
new owners/fallbacks/adapters/branches, retirement, evidence freshness, and any
readiness locks. Allowed decisions are continue, pause-for-user,
needs-baseline-readback, needs-verification, and blocked.
Never emit gate-passed, completion-granted, or authoritatively-safe.
Before a completion claim:
aegis:verification-before-completion.durable-work-guidance.md for the completion
bundle and structural workspace check.Generated packs are future-runtime inputs only. Method Pack output remains verified evidence and advisory judgment, not authoritative completion.
Report naturally and omit empty structures. Keep these semantic slots visible:
Aegis Visibility; current todo/active/completed/next; baseline usage decision;
readiness state when present; fresh evidence; inherited-claim corrections when
a resumed record overstated its state; retry/convergence state when
relevant; drift decision; risk/unknown; and the next smallest safe action.
Use when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion.
---name: long-task-continuationdescription: Use when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state…---# skills/long-task-continuation/SKILL.mdFAQ
Téléchargez skills/long-task-continuation/SKILL.md auprès de l'éditeur, ou copiez le chemin et ouvrez le dépôt. PlugMCP répertorie le skill et n'héberge pas le fichier.
L'éditeur le maintient sur https://github.com/GanyuanRan/Aegis.
Claude, Cursor, Codex et Grok Build peuvent lire un SKILL.md que vous ajoutez depuis le dépôt de l'éditeur. Grok Bot l'installe lorsque vous envoyez dans un chat le lien du dossier GitHub du skill.