From hb
Verifies implementation progress against a plan by checking done-when items, running tests, and identifying blockers. Shows per-phase progress with cursor at first incomplete phase.
How this skill is triggered — by the user, by Claude, or both
Slash command
/hb:check [slug][slug]The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Verify plan checkboxes against the codebase. Unmark items that don't hold up (`[x]` → `[ ]`).
Verify plan checkboxes against the codebase. Unmark items that don't hold up ([x] → [ ]).
Interactive prompts: present options as a numbered list and wait for the user's choice.
The argument (if provided) is: $ARGUMENTS
Use the argument as <slug> if given. Accepts slug or @file reference.
If no argument is provided, list available plans as numbered options and wait for the user's choice.
Count - [x] and - [ ] lines under each ## Phase N heading. Per-phase: Phase N — title: checked/total. Sum → Total: checked/total.
Read .specs/plans/<slug>.md. If missing, list plans as numbered options and wait for the user's choice.
If primary module file(s) from Phase 1 don't exist, skip subagent — report 0/N — not yet started, list Phase 1 done-when items.
Use a general-purpose subagent (not code-review). The subagent must be read-only (no file writes, no edits). It should:
- [ ] / - [x] item against the codebase[x]) or unchecked ([ ])Collect findings into two categories:
Using the subagent's report, update each checkbox in .specs/plans/<slug>.md:
[x][ ] (unmark)Count progress per phase (Progress Algorithm), then print:
## Verification: <slug>
### Progress
Phase 1 — title: checked/total
> Phase 2 — title: checked/total
Total: checked/total
The > marks the first incomplete phase (cursor).
### BLOCKERS
- (list or "None")
### SUGGESTIONS
- (list or "None")
If all items verified (total checked = total):
All phases complete — implementation verified.
If blockers exist, list items to fix, then re-run /hb:check <slug>.
If all items verified, suggest creating a PR or shipping.
npx claudepluginhub helderberto/agent-skills --plugin hbAudits post-implementation plans against changes by parsing checkboxes for completeness and accuracy. Supports autonomy modes (Autopilot, Critical, Verbose) and file-review. Invoke via /verify-plan.
Verifies code implementation against plan document: reads plan from disk, inspects codebase independently, runs full tests. Outputs structured PASS/FAIL review to file. Use post-execution.
Verifies plan completion by checking task status, running tests, measuring coverage, building, linting, and checking file sizes. Outputs a verification report.