Recall relevant past failures, prevention rules, and context packs before starting a coding task.
Scanned 9/3/2026
Install to Claude Code
npx -y skills add IgorGanapolsky/ThumbGate --skill recall-context --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Recall Context?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/igorganapolsky-recall-context)More formats (shields.io, HTML) on the badges page.
---
name: recall-context
description: Recall relevant past failures, prevention rules, and context packs before starting a coding task.
---
# Recall Context
Retrieve relevant historical context before beginning work on a coding task.
## When to use
- Starting a new coding task or feature
- Before making changes to code that has failed before
- Resuming work from a previous session
## How it works
Use the `recall` MCP tool to retrieve:
1. **Prevention rules** — Rules auto-promoted from repeated failure patterns that apply to the current task.
2. **Past failures** — Specific failure events with context, tags, and corrective actions.
3. **Context packs** — Bundled project context from previous sessions.
## Example
```
Use the recall MCP tool to check for known issues with the authentication module before refactoring.
```
The tool returns structured context that helps avoid repeating past mistakes and surfaces corrective actions from promoted lessons.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...