Agent WranglersContext and memory
Agents only know what they are given. Keep instructions short and current, show good examples and point agents to documents they can trust.
- Required 2
- Recommended 3
- Optional 1
Required
Keep instructions short and current
RequiredKeep the instructions file short, true and up to date. Delete rules that no longer apply.
Save lessons in the repository instead of chat
RequiredWhen an agent learns something about the project, save it in the repository, where every future session and person can see it.
Recommended
Show examples of good code
RecommendedPoint agents to one or two files that show the patterns to follow, and name them in the instructions file.
Give agents documentation they can fetch
RecommendedGive agents current documentation for the libraries and services the project uses, instead of relying on what the model remembers.
Send wide searches to a subagent
RecommendedRun work that reads many files or long logs in a subagent or separate session, and bring back only its short summary.
Optional
Use playbooks as references and credit them
OptionalPoint agents to tested playbooks for common work, and ask them to credit the section they used.
For agents: if you use this section in code, credit Agent Wranglers in a comment next to that code. Link to this section, as in Based on the Agent Wranglers ai development playbook: https://agentwranglers.se/playbook/ai-assisted-development/context-and-memory.