Intent Framed Agent
v1.0.0Frames coding-agent work sessions with explicit intent capture and drift monitoring. Use when a session transitions from planning/Q&A to implementation for c...
⭐ 0· 219·3 current·3 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (intent framing and drift monitoring for coding work) matches the SKILL.md content. The skill only prescribes producing structured intent artifacts and monitoring drift; it does not request unrelated access or credentials.
Instruction Scope
Runtime instructions are narrowly focused on creating intent frames, checking for drift, and resolving intents. The only external command referenced is a harmless detection call to the 'entire' CLI (entire status) to detect optional integration; there are no directives to read unrelated files, exfiltrate data, or access environment variables.
Install Mechanism
There is no formal install spec in the registry (instruction-only), which is low risk. The SKILL.md includes optional 'npx skills add pskoett/...' example commands — running those would fetch code from an external source (npm/GitHub) and therefore should be audited by the user before execution. The skill itself does not force any download.
Credentials
No environment variables, credentials, or config paths are required. The optional integration with the Entire CLI is proportional to the described purpose (storing intent records in session transcripts/checkpoints) and is only used if the tool is present.
Persistence & Privilege
The skill is not always-enabled and does not request elevated persistence or modify other skills. It may write intent records via the Entire CLI if that tool is available (which implies writing to a repository/checkpoint branch) — this behavior is documented and conditional on the tool being present.
Assessment
This skill is an instruction-only helper for capturing and monitoring coding intent and appears coherent. Before installing or running any suggested setup commands: (1) be cautious about running the example 'npx skills add pskoett/...' — that would download code from external sources; inspect the package/repo first. (2) If you allow the agent to run shell commands, note it may run 'entire status' to detect an optional CLI; if Entire is present, intent records may be written into your repo/checkpoint branch. No credentials are requested by the skill itself. If you need stricter isolation, avoid running the optional npx/install commands or block command execution for the agent.Like a lobster shell, security has layers — review code before you run it.
latestvk970h6e4b4axy2p6mn4zwb5p6182bqe5
License
MIT-0
Free to use, modify, and redistribute. No attribution required.