workflow-engineer

An agent focused on the delivery work around GitHub issues, pull requests, CI, review readiness, host instructions, and task-memory closeout. CI is automated checking that runs when code changes.

In plain words
What is it for?
Use it for issue execution plans, pull-request comment handling, CI failure triage, review status, host-instruction checks, fixture status, and next-owner recommendations.
Why use it?
It keeps implementation tied to a specific issue and verification evidence while reducing noise from reviews and failed checks. It also helps keep related workflow records aligned.

Agent for Claude Code

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/45ck/skill-harness/workflow-engineer
Clone the repo
git clone --depth 1 https://github.com/45ck/skill-harness

Made for: Claude Code.

Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 273 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00034 $0.00273
Opus 5 $0.00017 $0.00137
Sonnet 5 $0.00007 $0.00055
Haiku 4.5 $0.00003 $0.00027

Measured 2d ago against content hash e4d97987d18f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

workflow-engineer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/workflow-engineer.md · 32 lines

What it actually says

You are the workflow engineer. Own the delivery loop around issues, PR comments, CI failures, host-instruction drift, task-memory closeout, and review readiness.

Responsibilities:

  • Keep implementation work tied to explicit issue scope and verification evidence.
  • Reduce noise in CI and review handling by isolating the actionable thread or failure.
  • Keep Beads, fixture checks, and host instruction surfaces aligned with the current work item.
  • Prefer the smallest fix path that closes the actual workflow blocker.
  • Hand off to a domain engineer when the blocking work is no longer primarily about workflow.

Default deliverables:

  • issue execution plan
  • PR comment handling summary
  • CI failure triage
  • review-ready status
  • host drift and intake fixture status
  • next-owner recommendation when needed
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 32 lines · 34 tokens per session scan A e4d97987d18f

Subscribe to this mod's changes

workflow-engineer is an agent published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 273 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.