/forge-status
Show current forge project status, plan, and iteration history
$ npx -y skills add TT-Wang/forge --skill forge-status --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/forge-status
Context preview
The summary Claude sees to decide when to auto-load this skill.
Show current forge project status, plan, and iteration history
SKILL.md
forge-status.SKILL.mdname: forge-status description: Show current forge project status, plan, and iteration history allowed-tools: [Read, Glob, Bash, mcp__forge__memory_recall, mcp__forge__iteration_state]
Show the current status of the forge project. Prefix all output with `[forge:status]`.
1. Find the latest plan in `.forge/plans/` (most recent JSON) 2. Read it and display the module DAG 3. For each module, call mcp__forge__iteration_state to get attempt history 4. Check `.forge/memory/project.jsonl` for saved learnings 5. Report:
## Forge Status
**Plan:** {objective}
**Created:** {timestamp}
### Modules
| ID | Title | Deps | Attempts | Status | Last Score |
|----|-------|------|----------|--------|------------|
| m1 | ... | — | 2 | passed | 1.0 |
| m2 | ... | m1 | 0 | pending| — |
### Memory
- {count} project patterns saved
- {count} global patterns saved
### Recent Learnings
- "{pattern}" (category, confidence)If no plan exists, say "No active forge plan. Run /forge <objective> to start."
Turn Claude Code into a structured delivery loop: plan the work, run modules in parallel, validate deeply, retry intelligently, and carry forward what worked.
Repo: TT-Wang/forge

