Self-Direction
v1.0.0Your agent learns to think like you. Captures your direction system, makes decisions as you would, guides all processes toward your goals.
⭐ 0· 328·0 current·0 all-time
byIván@ivangdavila
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (capture a user's decision rules and transmit them to sub-agents) align with what the skill asks for: no external credentials, no unrelated binaries, and an explicit config path (~/self-direction/) where the model and evidence are stored. The declared metadata includes the same config path.
Instruction Scope
SKILL.md directs the agent to observe interactions, extract decision patterns, and write multiple files under ~/self-direction/ (direction.md, evidence.md, transmission.md, etc.). It does not instruct network exfiltration or access to other system credentials, but it does encourage continuous logging of user choices and corrections — this can capture sensitive context or decision-related content. The instructions are broad about 'watch your decisions' which could mean monitoring many interactions; that breadth is expected for this purpose but privacy-sensitive.
Install Mechanism
Instruction-only skill with no install steps, no binaries downloaded, and no code written to disk by the installer — lowest-risk install posture. All behavior is driven by the SKILL.md runtime instructions and writing under the user's home directory.
Credentials
The skill requests no environment variables, credentials, or external config paths beyond the declared ~/self-direction/ directory. That scope is proportionate to its stated purpose of creating and maintaining a local model of the user's direction system.
Persistence & Privilege
The skill intentionally creates persistent local files and templates under ~/self-direction/ to store an evolving model and evidence. It does not set always:true and does not request elevated system privileges, but because the model is persistent and the skill allows autonomous agent invocation (platform default), the agent may act later based on stored direction data — consider this when assessing risk.
Assessment
This skill is internally coherent with its purpose, but it stores persistent logs and a model of how you make decisions in ~/self-direction/, which can include sensitive context. Before installing or enabling it, consider: (1) Do you trust the agent/process that will read and update those files? (2) Review the ~/self-direction/ files regularly and delete or redact anything sensitive. (3) If needed, restrict file permissions or store the directory on encrypted storage. (4) Limit what the agent is allowed to observe (avoid automatic logging of private chats, credentials, or financial data). (5) If you want tighter control, require explicit approval for high-stakes decisions and configure clear escalation triggers in the transmission frames. If any of these are unacceptable or unclear, treat the skill as privacy-sensitive and review or decline installation.Like a lobster shell, security has layers — review code before you run it.
latestvk9798enwcytpyfgmhqaadnr6fs81t7h6
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🧭 Clawdis
OSLinux · macOS · Windows