AgentStack
SKILL verified MIT Self-run

Context Engineering Planner

skill-45ck-skill-harness-context-engineering-planner · by 45ck

Plan the context, artifacts, memory, retrieval, and compression surfaces needed for an agent workflow or long-horizon task.

No reviews yet
0 installs
12 views
0.0% view→install

Install

$ agentstack add skill-45ck-skill-harness-context-engineering-planner

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No 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 Context Engineering Planner? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Context Engineering Planner

Use this skill when an agent workflow needs deliberate context design instead of a large undifferentiated prompt.

Plan

  • Identify the decision the agent must make and the evidence it needs.
  • Split context into durable source, transient working context, generated evidence, and memory candidates.
  • Prefer repo files, issues, manifests, tests, traces, and docs over prose recollection.
  • Define what may be retrieved automatically and what must be explicitly requested.
  • Define what should be compressed, summarized, or excluded.
  • Name stale-context risks and refresh checks.

Context Classes

  • source: canonical specs, code, issues, policies, manifests
  • evidence: tests, logs, screenshots, traces, evaluation results
  • memory: reusable lessons worth recording with the project memory mechanism
  • working: temporary notes used only for the current run
  • excluded: secrets, private data, raw traces, irrelevant history, stale generated output

Output

Workflow Goal

Required Source Context

Evidence Inputs

Retrieval Plan

Compression Plan

Memory Candidates

Exclusions

Refresh Checks

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.

Versions

  • v0.1.0 Imported from the upstream source.