← Browse
llm-tooling
Kalabint ★ 6
This plugin provides 23 hooks and 19 skills that intervene at turn boundaries to block common LLM failure modes such as false acknowledgments, ungrounded claims, and context poisoning. It works by pre- and post-processing user and model interactions with bash-based guard rules that remind the model to stay factual and re-run corrected outputs when necessary.
Install
> /plugin marketplace add Kalabint/llm-tooling
> /plugin install llm-tooling
What it's made of
19 skills · 23 hooks
- Commands
- 0
- Agents
- 0
- Skills
- 19
- MCP servers
- 0
- Hooks
- 23 · PostToolUse, PreCompact, PreToolUse, SessionStart, Stop, UserPromptSubmit
What it needs & plugs into
- API keys
- none
- Paid services
- none detected
- External tools
bash- Talks to
- nothing external detected
Analyzed . Facts extracted from the plugin's files. Prose generated by claude-haiku-4-5-20251001.
Is this your plugin?
Claim it to keep the card accurate and enter the weekly contest. Requires signing in as the GitHub owner (Kalabint).