spiral
Spiral
The methodology for sustaining a multi-week autonomous PR loop without the agent losing context, running out of work prematurely, or accumulating debt.
The agent does not remember the project. The project remembers itself. Every kind of state lives in git-tracked ledger files with rigid templates. The agent's job collapses to: read ledgers, pick the next slice, run the loop, update ledgers. Every iteration returns to the same artifacts and finds them advanced. The shape is not a loop, it is a spiral: forward-while-circling.
When to invoke
/spiral init: at the start of a fresh project. Writes the canonical scaffold (rules, plan, agreement, GDD tree, coverage ledger, progress log, open questions, followups, playtest, fun-factor audit) into the current repo./spiral audit: on an existing project. Diffs the repo against the canonical structure and prints a remediation checklist. Catches the three known failure modes (monolith GDD, chapter-granular coverage, missing qualitative gate) plus generic drift (stale progress log, missing ledgers, open questions without recommended defaults, followups without priorities).
Per-slice execution (read context, branch, implement, PR, merge, repeat) is the job of randroid:loop. Per-task tracking is the job of task-tracking-dots. This skill is the substrate those two run against.
Why this exists: the three case studies
Three multi-week autonomous-loop projects produced three outcomes. The pattern is in docs/case-studies.md. The short version: