.claude/skills/token-disciplineRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
Stop wasting context on the agent's own output. Applies when running diagnostic commands, reading files, or summarizing findings: filter tool output before it enters the transcript, never re-quote what the reader can already see, and state conclusions once. Invoke with /token-discipline; stays on until "normal tokens".
These states come from the source or distribution context. None of the entries below are SkillVetAI compatibility test results.
These checks parse the fixed package against dated platform rules. They do not execute the Skill or verify task behavior.
.claude/skills/token-disciplineRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
.agents/skills/token-disciplineRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
skills/token-disciplineRuntime, accounts, dependencies, permissions, network behavior and task quality remain untested.
This command is recorded from the source ecosystem and resolves the registry's latest release. The fixed release shown on this page should be inspected before adoption.
clawhub install @147258xuan/token-disciplineclawhub inspect @147258xuan/token-discipline --version 0.1.0This automated, non-executing scan is bound to this release hash. It is not a safety certification and may contain false positives or false negatives.
This is registry-supplied evidence for the recorded release, not an independent SkillVetAI scan. Check the canonical source for the full report, scanner versions, scope, and current moderation state.
The catalog stores hashes and an inventory summary for change detection. It does not republish the package contents.
sha256:217c0436b764af896933763b61f1ef250d66e7fd2845df4f1c75606b7440c764skill-card.mdSKILL.md- Added `token-discipline`, a `/token-discipline` skill for reducing context spent on tool output and repetition. - Sets a default cap of about 30 lines per command and encourages filtering output at the source. - Covers concise conclusions, verification labels, reading files efficiently, batching checks, and avoiding redundant re-verification. - Advises against saving turn-specific findings to persistent memory.