From agentops
Executes a single tracked issue end-to-end using TDD per slice. Useful when implementing a specific issue, picking up ready work, or running an ad-hoc task.
How this skill is triggered — by the user, by Claude, or both
Slash command
/agentops:implementThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> **Quick Ref:** Execute single issue end-to-end. Output: code changes + commit + closed issue.
Quick Ref: Execute single issue end-to-end. Output: code changes + commit + closed issue.
YOU MUST EXECUTE THIS WORKFLOW. Do not just describe it.
Move 4 (TDD per slice) of the operating loop. Consumes one vertical slice from the slice validation plan; produces failing test → passing implementation → refactor-under-green. Discipline: (1) first failing test must fail for the right reason (missing behavior, not syntax); (2) smallest change to flip green; (3) refactor as its own commit. Slices that mix refactor + feature are two slices, not one. Code without a failing test has no contract; the slice is not done.
Execute a single issue from start to finish.
CLI dependencies: bd (issue tracking), ao (ratchet gates). Both optional — see skills/shared/SKILL.md for fallback table. If bd is unavailable, use the issue description directly and track progress via TaskList instead of beads.
/implement <issue-id> to implement a specific tracked issue./implement (no argument) to pick up next ready work via bd ready./implement <description> to implement an ad-hoc task without a tracked issue.pr-implement routes herepr-implement → OSS contribution mode. Use when you need to implement a scoped OSS PR —
fork-based implementation of an open source contribution with mandatory isolation checks.
Same single-issue TDD discipline as internal work, plus the fork lane: ensure the fork exists
and is current, create an isolated worktree, run an isolation pre-check (BLOCK on mixed
concerns) and post-check (BLOCK on scope creep), check for competing PRs before starting, and
hand off to /pr-prep for commit/PR shaping. Input is the plan artifact from /pr-prep +
/plan (run those first if no plan exists).User says: /implement ag-5k2
What happens:
middleware/auth.go to add token validationgo test ./middleware/... — all tests passbd close ag-5k2 --reason "commit:<sha> files:[middleware/auth.go]"Result: Issue implemented, verified, committed, and closed. Ratchet recorded.
User says: /implement
What happens:
bd ready — finds ag-3b7 (first unblocked issue)bd update ag-3b7 --status in_progressResult: Autonomous work pickup and completion from ready queue.
User says: /implement ag-8h3 (invoked by /crank --test-first)
What happens:
Result: Minimal implementation driven by tests, no over-engineering.
| Flag | Default | Description |
|---|---|---|
--no-lifecycle | off | Skip ALL lifecycle skill auto-invocations (test gen, review, refactor) |
--lifecycle=<tier> | matches complexity | Controls which lifecycle skills fire: minimal (test only), standard (+review), full (+refactor dry-run) |
Lifecycle tier defaults to matching the current complexity level. Explicit --lifecycle=<tier> overrides.
Read references/workflow.md when you need the full step-by-step procedure (Steps 0 through 8, including pre-flight gates, TDD discipline, build/security verification, the binary-deployment gate, the verification iron law, commit, close, and ratchet record).
GREEN mode rules live in references/green-mode.md. The pre-commit autonomous quality loop lives in references/quality-loop.md. The behavioral spec format lives in references/behavioral-spec.md.
--no-tdd)--no-lifecycle)If bd CLI not available:
Per the output_contract in frontmatter: code changes, test results, bead status update, and behavioral spec (optional).
<promise>DONE</promise>
If blocked or incomplete:
<promise>BLOCKED</promise>
Reason: <why blocked>
<promise>PARTIAL</promise>
Remaining: <what's left>
| Problem | Cause | Solution |
|---|---|---|
| Issue not found | Issue ID doesn't exist or local state looks stale | Run bd show <id> to verify; use bd vc status only if you need Dolt state |
| GREEN mode violation | Edited a file not related to the issue scope | Revert unrelated changes. GREEN mode restricts edits to files relevant to the issue |
| Verification gate fails | Tests fail or build breaks after implementation | Read the verification output, fix the specific failures, re-run verification |
| "BLOCKED" status | Contract contradicts tests or is incomplete in GREEN mode | Write BLOCKED with specific reason, do NOT modify tests |
| Fresh verification missing | Agent claims success without running verification command | MUST run verification command fresh with full output before claiming completion |
| Ratchet record failed | ao CLI unavailable or chain.jsonl corrupted | Implementation still closes via bd, but ratchet chain needs manual repair |
npx claudepluginhub boshu2/agentops --plugin agentopsGuides an 8-step agentic development workflow for issues: parsing, loading issue-type skills, reading specs, planning, implementing, testing, opening PRs/MRs, and addressing review.
Executes GitHub issues by reading content with read-github-issue, delegating tasks to frontend-implementer or general-purpose-assistant sub-agents, running tests/lint, committing on worktree, and creating PRs via commit-push and create-pr.