Loading...
Loading...
Verification boundary CLI that delegates tasks to autonomous agents. Use when the user wants to run forge, execute specs, run specs in parallel, audit code against specs, review changes, watch live logs, check run status, resume a session, or delegate complex multi-step work to an autonomous agent. Triggers include "forge run", "run this spec", "run specs in parallel", "audit the codebase", "review changes", "forge watch", "forge status", "rerun failed", "delegate this to forge".
npx skill4agent add vieko/forge forge-C ~/other-projectforge run "add auth middleware" # Simple task
forge run --spec specs/auth.md "implement this" # With spec file
forge run --spec-dir ./specs/ -P "implement all" # Parallel specs
forge run -C ~/other-repo "fix the login bug" # Target different repo
forge run --rerun-failed -P "fix failures" # Rerun failed specs
forge run --resume <session-id> "continue" # Resume interrupted session
forge "quick task" # Shorthand (no 'run')-s, --spec <path>-S, --spec-dir <path>.md-P, --parallel--sequential-first <n>-C, --cwd <path>-w, --watch--dry-runforge run --helpforge run --spec-dirforge audit specs/ # Audit, output to specs/audit/
forge audit specs/ -o ./remediation/ # Custom output dir
forge audit specs/ -C ~/target-repo # Different repoforge review # Review main...HEAD
forge review HEAD~5...HEAD # Specific range
forge review --dry-run -o findings.md # Report only, write to fileforge watch # Watch latest session
forge watch <session-id> # Watch specific sessionforge status # Latest run
forge status --all # All runs
forge status -n 5 # Last 5 runs# 1. Write specs as .md files (see references/writing-specs.md)
# 2. Run them in parallel
forge run --spec-dir ./specs/ -P "implement all specs"
# 3. Rerun any failures
forge run --rerun-failed -P "fix failures"
# 4. Check results
forge statusforge run --spec-dir ./specs/ -P --sequential-first 2 "implement"
# Runs 01-*.md, 02-*.md sequentially, then 03+ in parallelforge audit specs/ -C ~/project # Find gaps
forge run --spec-dir specs/audit/ -P -C ~/project "fix remaining"forge run --resume <session-id> "continue" # Pick up where you left off
forge run --fork <session-id> "try different approach" # Branch from that point| Reference | Load when |
|---|---|
| writing-specs.md | Writing spec files for forge to execute |
| parallel-execution.md | Tuning concurrency, understanding cost, monitoring parallel runs |