Context Rot -- Your Agent Has Been in This Chat Too Long
Persona
Detect stale assumptions, buried decisions, instruction drift, and conversational brain damage.
About
Your agent remembers everything except which parts still matter.
Context Rot diagnoses long-running chats, project threads, and handoffs that have accumulated stale assumptions, rejected drafts, repeated tool output, and contradictory instructions. It separates what is still canonical from what needs verification, resolution, or retirement.
What you get
- A verdict: FRESH, STALE AROUND THE EDGES, CONTEXT ROT, or COMPOST THE THREAD
- Canonical facts and decisions that still affect the work
- Stale observations that need current verification
- Contradictions preserved for explicit resolution
- Context bloat that can safely stay out of the next session
- A compact restart packet with objective, constraints, sources, open decision, and next action
It does not delete files or memory, flatten disagreements, or carry credentials forward. Old context is not automatically bad; unsupported context that keeps changing decisions is.
Use Context Steward for durable memory governance. Use Context Rot when the immediate thread has become the problem.
Core Capabilities
- Classify canonical, stale, contradictory, bloated, and missing context
- Detect instruction drift and buried decisions
- Produce a compact restart packet
- Recommend when recurring context should become durable tooling
Customer ratings
0 reviews
No ratings yet
- 5 star0
- 4 star0
- 3 star0
- 2 star0
- 1 star0
No reviews yet. Be the first buyer to share feedback.
Version History
This persona is actively maintained.
September 30, 2026
Initial release — diagnose context decay and create a clean restart packet.
One-time purchase
$9
By continuing, you agree to the Buyer Terms of Service.
Creator
Brian Gorzelic — SpookyJuice.AI
Evidence-led tools for AI agents, software releases, and technical operations
Built from real operating workflows, with provenance, safety boundaries, and human approval designed in.
View creator profile →Details
- Type
- Persona
- Category
- Productivity
- Price
- $9
- Version
- 1
- License
- One-time purchase
Works With
Works with OpenClaw, Claude Projects, Custom GPTs and other instruction-friendly AI tools.
Recommended Skills
Skills that complement this persona.
Slop Mop -- Clean AI Output Before Someone Else Has To
Productivity
Remove filler, fake certainty, repetition, and recipient-shifted work without losing the useful core.
$9
Approval Interrupts -- Automate Right Up to the Line
Productivity
Put human approval exactly before sends, publishes, charges, deploys, merges, and deletes.
$5
Opportunity Sourcing Engine -- Fewer Leads, Better Evidence
Productivity
Find employer-verified opportunities, map real fit, flag stale evidence, and prepare human-approved next moves.
$39