القائمة
Systematic debugging playbook for the Forge agentic loop (src/core/loop.ts and src/agents/executor.ts). Use when a task is stuck, looping, or producing wrong tool calls.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
Deep review — random exploration + cross-agent review, alternating. Finds integration bugs that self-review misses. Run every 30–60 min during active implementation.
Overview of Forge's Agentic Coding Flywheel methodology. Use to route between plan, bead, and code space. See FLYWHEEL.md at the repo root.
End-of-session ritual. Close finished beads, file new ones for remaining work, run verify, commit in logical groupings, push. Work is not complete until git push succeeds.
Start a new Flywheel planning round. Produce initial markdown plan, route to competing frontier models, synthesize hybrid, refine 4–5×. Use before any coding begins on a new feature.
Translate a polished markdown plan into self-contained beads in .beads/beads.jsonl. Every bead must be executable without reopening the plan. Use after the plan has converged.
Polishing pass over all open beads. Run 4–6 times. "Check your beads N times, implement once." Use after plan-to-beads and between refinement rounds.
| name | debug-loop |
| description | Systematic debugging playbook for the Forge agentic loop (src/core/loop.ts and src/agents/executor.ts). Use when a task is stuck, looping, or producing wrong tool calls. |
The loop is the single most expensive place to be wrong. Before you change anything, instrument.
FORGE_LOG_LEVEL=debug ./bin/forge.js <command>.~/.config/forge/events/<session>.ndjson.FORGE_MODEL=... FORGE_ROUTER_FALLBACK=0.Each turn emits: turn.start, model.call, tool.call, tool.result,
validation.result, turn.end. If any stage is missing or out of
order, that is your bug. Grep the ndjson before staring at code.
src/core/mode-policy.ts) — is the agent hitting the
turn/token cap and being cut off? The event will say so.src/core/validation.ts) — is the gate
rejecting a valid step? Look at validation.result.reason.tool.call with class: not_found means no.tool.result.denied=true in the stream.src/persistence/tasks.ts) — is an illegal
transition being attempted?callModel mocked.test/unit/executor-loop.test.ts
is the template.Run /verify. If the test you added doesn't turn green, you fixed the
wrong thing.