| name | task-state-ledger |
| description | Maintain a portable task-state ledger for long, multi-step work. Use when a task spans many files, produces large logs, needs a reliable handoff, or requires traceable evidence without repeatedly loading full outputs. Creates concise state records and private evidence references with explicit limits, redaction checks, and retention guidance. |
| license | MIT |
| metadata | {"version":"1.1.0"} |
Task State Ledger
Maintain a compact record of active work and a separate local evidence ledger. Use this skill to improve continuity and traceability during long tasks. Do not describe it as automatic memory, a context-window optimizer, or a promise of token savings.
Operating limits
This skill records information only when the current environment can read and write the selected files. It cannot recover information that was never recorded, alter a host application's memory, or make hidden conversation history available.
Treat every recorded artifact as potentially discoverable. Do not save credentials, private keys, session cookies, access tokens, personal information, customer data, or unredacted environment files.
Persistent availability and use
Install this skill at the workspace or user level when the client supports persistent skills. Persistent installation makes the workflow available in each compatible session. It does not require automatic execution or override the client's own conversation history.
For consistent use, keep this short rule in the active project guidance:
For multi-step work, use Task State Ledger before loading large output. Record the current task state and retrieve only the evidence needed for the next decision.
