— No reviews yet
0 installs
15 views
0.0% view→install
Install
$ agentstack add skill-45ck-skill-harness-task-memory-profile-planner ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Are you the author of Task Memory Profile Planner? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claimAbout
Task Memory Profile Planner
Use this skill when deciding how a repo should preserve agent task state across sessions, branches, worktrees, and tools.
Process
- Identify who owns task state: human maintainer, agent team, external tracker, or local repo.
- Decide whether the repo needs durable issue graphs, dependency edges, worktree coordination, persistent memories, or only lightweight plan files.
- Compare options:
- Beads for repo-local graph issues and agent session continuity
- lightweight checked-in plan/evidence files
- external tracker such as GitHub Issues, Linear, Jira, or Azure DevOps
- no durable task memory yet
- Define sync, conflict, branch, and closeout rules.
- Record what must never be stored: secrets, raw private tickets, broad mailbox data, private traces, or unredacted customer content.
- Tie the selected memory profile to installer flags and setup proof.
Output
Task-State Owner
Required Memory Shape
Selected Profile
Installer Flags
Sync And Closeout Rules
Privacy Exclusions
Evidence Path
Avoid
- enabling Beads only because it is available
- storing private operational context in generated traces
- mixing task memory with long-term model memory without an explicit policy
- leaving closeout rules separate from the repo's normal quality gates
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: 45ck
- Source: 45ck/skill-harness
- License: MIT
- Homepage: https://github.com/45ck/skill-harness/releases/tag/v0.1.0
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.