Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From A2Z FORGE
Run bounded persistent orchestration until a milestone, blocker, budget boundary, deadline, or user stop. Use for autonomous continuation with explicit limits.
How this skill is triggered — by the user, by Claude, or both
Slash command
/a2z-forge:forge-loopThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Read \`${CLAUDE_PLUGIN_ROOT}/references/WORKFLOW_PROTOCOL.md\` before mutating project state.
Read `${CLAUDE_PLUGIN_ROOT}/references/WORKFLOW_PROTOCOL.md` before mutating project state.
milestone or stop condition; budget; deadline; agent limit; permission mode.
continuous journal; checkpoints; completed tasks; consolidated blockers; safe stop state.
Recompute ready work and critical path each cycle. Keep productive workers bounded by leases. Reassign idle capacity to valid review or research. Stop on policy, budget, diminishing returns, or dependency deadlock. Never loop merely to appear active.
Honor the current permission mode. Use only task-relevant tools and installed skills. Log consequential actions. Persist outputs before reporting success.
On tool failure, record the command, safe retry state, and blocker. Retry only idempotent work. Never convert a missing credential, unavailable provider, failed test, or incomplete adapter into a success claim.
`/forge-loop --milestone foundation --budget 10 --agent-limit 3`
A fixture with no ready work stops once, reports the blocker, and does not consume repeated model calls.
npx claudepluginhub jumpsy/a2z-forge --plugin a2z-forgeGuides completion of development work by verifying tests, detecting environment, and presenting structured options for merge, PR, or cleanup.
Enforces test-driven development: write failing test first, then minimal code to pass. Use when implementing features or bugfixes.
Guides creation and editing of skills using test-driven development with pressure scenarios and subagents to verify agent compliance.