Home / ganyuanran / aegis · skills/long-task-continuation/SKILL.md · GitHub

long-task-continuation skillA

long-task-continuation is agent-read markdown (skill) from ganyuanran/aegis: Use when a task is multi-step, may span context resets or sessions, uses subagents, or risks losing state before completion..

Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.

What the file says

# Long Task Continuation

## Overview

Keep long work checkpointed, resumable, drift-aware, and evidence-gated. This
protocol does not execute plans, dispatch subagents, run tests, or grant
completion authority.

## Authority Boundary

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.

## When To Use

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:

- use a durable `work/` record for medium+ work that actually crosses sessions,
  needs handoff, or requires resumable state;
- otherwise keep one inline checkpoint.

Multi-step, todo-driven, possible-compaction, and subagent use do not force
durable records by themselves. Do not create both carriers or a record per
slice.

## Required Artifacts

A durable task has one process trail under
…

Read the whole file at its exact version.

How to install

Latest version
mdr add ganyuanran/aegis/long-task-continuation@git:20260916.9a51c7a
Exact content
mdr add ganyuanran/aegis/long-task-continuation@sha256:0e2957594ca31da6

Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_mrro7hknwpvjblv6.svg)](https://markdownregistry.com/a/art_mrro7hknwpvjblv6)

1 badge views in 30 days

Versions

versioncommittedcommitsizeaudit
git:20260916.9a51c7a latest2026-09-16 9a51c7a 8,543 BA view · diff
git:20260916.27321802026-09-16 2732180 8,219 BA view · diff
git:20260915.cce03832026-09-15 cce0383 13,892 BA view · diff
git:20260901.44ac08f2026-09-01 44ac08f 13,574 BA view · diff
git:20260811.11345da2026-08-11 11345da 12,142 BA view

Audit of the latest version

A  17 of 17 checks passed. Deterministic, no model, same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (8543 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

ganyuanran/aegis · 1,280 stars · license MIT · pushed 2026-09-24 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_mrro7hknwpvjblv6
GET https://markdownregistry.com/api/v1/resolve?ref=ganyuanran/aegis/long-task-continuation
GET https://markdownregistry.com/api/v1/blob/0e2957594ca31da63085271c9c5f28d680cd99a69804f23e49901e306ce932d0

Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

More from ganyuanran/aegis

AGENTS.md agents
ganyuanran/aegis · AGENTS.md
git:20260813.0c73270 · audit A · 1,280 stars
CLAUDE.md claude
ganyuanran/aegis · CLAUDE.md
git:20260813.0c73270 · audit A · 1,280 stars
anti-entropy-governance skill
ganyuanran/aegis · skills/anti-entropy-governance/SKILL.md · Use when touching retiring old logic, collapsing duplicate owners, removing fallbacks, or…
git:20260830.8e0cee3 · audit A · 1,280 stars
brainstorming skill
ganyuanran/aegis · skills/brainstorming/SKILL.md · Use when defining ambiguous or high-complexity new features, product behavior, UI/component design, architecture…
git:20260916.9a51c7a · audit A · 1,280 stars
communicating-concisely skill
ganyuanran/aegis · skills/communicating-concisely/SKILL.md · Use when the user asks for caveman mode, fewer tokens, brief responses, compressed communication, or otherwise…
git:20260723.88b8ec9 · audit A · 1,280 stars
dispatching-parallel-agents skill
ganyuanran/aegis · skills/dispatching-parallel-agents/SKILL.md · Use when facing 2+ independent tasks without a written plan, with no conflicting shared mutable state or sequential…
git:20260920.8265b5c · audit A · 1,280 stars
establishing-project-context skill
ganyuanran/aegis · skills/establishing-project-context/SKILL.md · Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or…
git:20260809.f62395b · audit A · 1,280 stars
executing-plans skill
ganyuanran/aegis · skills/executing-plans/SKILL.md · Use when executing a written implementation plan across sessions or with review checkpoints. Small or single-slice…
git:20260828.f7ae3a7 · audit A · 1,280 stars
finishing-a-development-branch skill
ganyuanran/aegis · skills/finishing-a-development-branch/SKILL.md · Use when verified work needs integration or cleanup of an existing task-created branch/worktree, or the user explicitly…
git:20260809.f62395b · audit A · 1,280 stars
first-principles-review skill
ganyuanran/aegis · skills/first-principles-review/SKILL.md · Use when asked for first-principles or Occam's-razor review, or when high-risk decisions involve competing constraints…
git:20260905.878cac9 · audit A · 1,280 stars
goal-framing skill
ganyuanran/aegis · skills/goal-framing/SKILL.md · Use when the user explicitly sets an Aegis goal with /aegis-goal, Aegis goal:, or asks to define goal, success…
git:20260723.88b8ec9 · audit A · 1,280 stars
receiving-code-review skill
ganyuanran/aegis · skills/receiving-code-review/SKILL.md · Use when receiving code review feedback before implementing suggestions, especially when feedback is unclear, risky…
git:20260723.88b8ec9 · audit A · 1,280 stars

Every file in ganyuanran/aegis

Browse by kind, by grade A, or by owner.