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.
npx agentmods add skills/addxai/enterprise-harness-engineering/dev-workflownpx skills add addxai/enterprise-harness-engineering --skill dev-workflowgit clone --depth 1 https://github.com/addxai/enterprise-harness-engineeringWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/addxai/enterprise-harness-engineering/dev-workflow)<a href="https://agentmods.dev/skills/addxai/enterprise-harness-engineering/dev-workflow"><img src="https://agentmods.dev/badge/skills/addxai/enterprise-harness-engineering/dev-workflow.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00109 | $0.05650 |
| Opus 5 | $0.00055 | $0.02825 |
| Sonnet 5 | $0.00022 | $0.01130 |
| Haiku 4.5 | $0.00011 | $0.00565 |
Grade A, and why
dev-workflow 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 618 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Workflow
Description
Standard R&D process orchestrator — guides the full development lifecycle from User Story to CD, with human confirmation required before proceeding to each step.
Collaboration with other skills: This skill is responsible for "what step are we on, what's next, and which skill to invoke"; architect handles "how to write the actual documents."
Every run must walk through the entire 9-step checklist — whether it is a new requirement, a new project, or a project already in progress — to ensure no critical step is missed (especially observability plans and test coverage).
Rules
- Mandatory full checklist: Every run must go from Step 1 to Step 9; no step may be skipped, even if its status is "Completed"
- Human confirmation at each step: After displaying the status of each step, wait for human confirmation (
[y/N]) before proceeding to the next - Observability is not optional: Step 5 (observability plan) is a required step and must not be skipped with "not needed for now"
- Documentation before code: Before Step 6 (TDD implementation), all documentation deliverables from Steps 1-5 must exist and be confirmed
- First-run initialization: When the project has no
CLAUDE.mdor no workspace skill, automatically run project initialization - All User Stories must have E2E coverage: In Step 4's test plan, every User Story must have a corresponding L3 E2E test case
Examples
Bad — Skipping undiscovered missing steps
User: "Code is all done, MR is merged, help me set up CD"
AI: Directly discusses CD configuration...
Problem: Skipped the observability plan (Step 5), test plan check (Step 4), etc., jumping directly to the step the user mentioned.
Good — Enforced full checklist
User: "Code is all done, MR is merged, help me set up CD"
AI:
── Step 1 — User Story ──────────────
Status: Completed
Deliverable: docs/product/user-stories/postcard.md
Do you want to update this step? [y/N (default: skip)]
...(Steps 2-4 display status similarly)...
── Step 5 — Observability Plan ──────────────
Status: Missing
Deliverable: docs/architecture/postcard/observability.md — does not exist
Do you want to update this step? [y/N (default: skip)]
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.
- 4d ago First seen · 618 lines · 109 tokens per session scan A db045e72eaf3
dev-workflow is a skill published in the GitHub repository addxai/enterprise-harness-engineering (44 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 109 tokens to every session and 5,650 once invoked, about $0.0005 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.
Other skills, from other repositories
peon-ping-toggle
Toggle peon-ping sound notifications on/off. Use when user wants to mute, unmute, pause, or resume peon sounds during a Claude Code session. Also handles config changes like volume, pack rotation, categories — any peon-ping setting.
peon-ping-log
Log exercise reps for the Peon Trainer. Use when user says they did pushups, squats, or wants to log reps. Examples - "/peon-ping-log 25 pushups", "/peon-ping-log 30 squats", "log 50 pushups".
meeting-transcript
Process meeting recordings and notes into structured decisions, action items, and team dynamics with intelligent noise filtering.
retro
CP-7 retrospective: audit checkpoints, evidence quality, action items, and harvest candidates. Closes the V-model cycle and feeds the next run. Use via /retro after ship, escalate, or significant session.
pad
Talk to your project. Natural-language project management — create items, check status, plan work, brainstorm ideas, and more.
pm-init
Skill "pm-init" from wei63w/pm-manager, covering user input, outline, 1. scaffold, 2. lifecycle and type and 3. detect spec kit (required).