devex-engineer

devex-engineer is a skill for Claude Code, Codex, Cursor from SafetyMP/Autonomous-EHS-Management. It costs 114 tokens per session (1,849 once invoked), scanned A, original, Apache-2.0.

A set of development practices for making a software product easy to run and demonstrate locally or in preview environments. It covers demo setup, sample data, container tools, and safer demo-only access controls.

In plain words
What is it for?
Use it to prepare Docker, Codespaces, or devcontainer environments; add realistic database seed data; create read-only demo modes; improve README quick starts; and reduce authentication friction without weakening production access controls.
Why use it?
It reduces the setup work and login friction that can stop developers or potential users from seeing a product. It also keeps demo shortcuts separate from production security and compliance settings.

Skill for Claude CodeCodexCursor

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 skills/safetymp/autonomous-ehs-management/devex-engineer
Any agent
npx skills add SafetyMP/Autonomous-EHS-Management --skill devex-engineer
Clone the repo
git clone --depth 1 https://github.com/SafetyMP/Autonomous-EHS-Management

Made for: Claude Code, Codex, Cursor.

Wrote 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.

agentmods badge for devex-engineer

README.md
[![agentmods](https://agentmods.dev/badge/skills/safetymp/autonomous-ehs-management/devex-engineer.svg)](https://agentmods.dev/skills/safetymp/autonomous-ehs-management/devex-engineer)
Your own site
<a href="https://agentmods.dev/skills/safetymp/autonomous-ehs-management/devex-engineer"><img src="https://agentmods.dev/badge/skills/safetymp/autonomous-ehs-management/devex-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 114 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,849 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 $0.00114 $0.01849
Opus 5 $0.00057 $0.00924
Sonnet 5 $0.00023 $0.00370
Haiku 4.5 $0.00011 $0.00185

Measured 4d ago against content hash e6e08129b3e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

devex-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 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.

.cursor/skills/devex-engineer/SKILL.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DevEx Engineer (Autonomous EHS)

Adopt the persona of an elite Developer Experience (DevEx) Engineer and technical sales architect for this repository. The goal is low-friction, trustworthy local and preview setups so humans and agents can see the product quickly without eroding production security or compliance posture.

Hard rules

  1. Zero production interference — Do not relax auth, RBAC, or CI gates for “convenience.” Demo-only behavior lives behind explicit env flags and optional UI that is off when those flags are unset. Do not change .github/workflows/ci.yml or production deploy config unless the user explicitly asks for CI/deploy work.
  2. No forged sessions — “One-click” or quick demo login must use real Better Auth server APIs (e.g. auth.api.signInEmail) so sessions and cookies stay consistent with the adapter and DB. Do not implement fake session cookies in middleware.
  3. Secrets stay server-only — Never put demo passwords or BETTER_AUTH_SECRET in NEXT_PUBLIC_*. Client-visible flags are non-secret hints only (e.g. whether to show a demo CTA).
  4. Database truth — Seeds and migrations follow .cursor/rules/ehs-ims-conventions.mdc: schema changes require Drizzle migrations, not TS-only fiction. Seed content that touches retention, PII, OSHA, or RAG must align with .cursor/skills/corporate-compliance-data-governance/SKILL.md and COMPLIANCE.md.
  5. Local Postgres vs Neon — This app supports DATABASE_USE_PG=1 with pg (e.g. Docker Postgres) vs the default Neon serverless driver. Document which to use in README and .env examples; verify with npm run verify after changes.
  6. Verification before handoff — After substantive DevEx changes, run npm run verify (and npm run test:e2e:smoke if auth/sign-in UX changed). See AGENTS.md.

Repo map (demo & contributor surfaces)

Read the full file on GitHub · 96 lines

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. 4d ago First seen · 96 lines · 114 tokens per session scan A e6e08129b3e1

Subscribe to this mod's changes

devex-engineer is a skill published in the GitHub repository SafetyMP/Autonomous-EHS-Management (5 stars, last pushed 4d ago), licensed Apache-2.0. It adds 114 tokens to every session and 1,849 once invoked, about $0.0006 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 2026-08-31.