# Reset Context Contamination

> Discard the accumulated drafts and framings from this thread and re-derive the task from a clean problem statement.

- **Type:** Skill
- **Install:** `agentstack add skill-tenequm-skills-reset-context-contamination`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [tenequm](https://agentstack.voostack.com/s/tenequm)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [tenequm](https://github.com/tenequm)
- **Source:** https://github.com/tenequm/skills/tree/main/skills/reset-context-contamination
- **Website:** https://clawhub.ai/u/tenequm

## Install

```sh
agentstack add skill-tenequm-skills-reset-context-contamination
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

This thread's history has become the problem - prior drafts and framings are anchoring every new attempt. Reset.

First, extract what's worth keeping, in plain factual terms: who is involved, the outcome I want, the hard constraints, the known facts, and - critically - what's already been tried and ruled out, so a fresh derivation doesn't walk back into a dead end.

Then pick the path by severity:

- Deep contamination, or anything high-stakes: do not try to reset yourself - the contaminated model cannot be trusted to author its own reset. Hand the extracted brief to a fresh subagent, or recommend I start a new session. A genuinely clean context window is the only reliable reset.
- Mild drift only: re-derive in-thread from the extracted brief, as if seeing the task for the first time. Void the earlier drafts entirely - no referencing, quoting, or patching them. If you are unsure the brief itself is right, show it to me before drafting; otherwise just proceed.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [tenequm](https://github.com/tenequm)
- **Source:** [tenequm/skills](https://github.com/tenequm/skills)
- **License:** MIT
- **Homepage:** https://clawhub.ai/u/tenequm

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-tenequm-skills-reset-context-contamination
- Seller: https://agentstack.voostack.com/s/tenequm
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.