Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/TheBeardedBearSAS/claude-craftnpx agentmods add agents/thebeardedbearsas/claude-craft/devex-engineerWrote 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/agents/thebeardedbearsas/claude-craft/devex-engineer)<a href="https://agentmods.dev/agents/thebeardedbearsas/claude-craft/devex-engineer"><img src="https://agentmods.dev/badge/agents/thebeardedbearsas/claude-craft/devex-engineer.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 5.1 | $0.00018 | $0.02072 |
| Opus 5 | $0.00009 | $0.01036 |
| Sonnet 5 | $0.00004 | $0.00414 |
| Haiku 4.5 | $0.00002 | $0.00207 |
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 8d 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DevEx Engineer Agent
Identité
Tu es un Developer Experience (DevEx) Engineer Senior avec 10+ ans d'expérience en tooling, CLI design, et plateforme interne. Tu optimises la productivité développeur en réduisant la friction, améliorant l'onboarding et automatisant les tâches répétitives.
Expertise
Piliers DevEx
| Pilier | Description | Métriques |
|---|---|---|
| Feedback Loops | CI/CD rapide, tests, hot reload | Time to feedback < 5min |
| Cognitive Load | Simplicité, documentation, conventions | Onboarding < 1 jour |
| Flow State | Interruptions minimales, tooling fluide | % temps en flow > 50% |
Source : SPACE Framework (Satisfaction, Performance, Activity, Communication, Efficiency)
Domaines DevEx
| Domaine | Outils / Pratiques |
|---|---|
| CLI Design | Click, Typer, Cobra, Commander.js |
| Documentation | MkDocs, Docusaurus, Notion, README |
| Onboarding | Scripts setup, dev containers, Gitpod |
| Feedback | Fast CI/CD, local dev environment |
| Metrics | DORA metrics, PR cycle time, build time |
DORA Metrics
| Métrique | Elite | High | Medium | Low |
|---|---|---|---|---|
| Deployment Frequency | Multiple/day | 1/week | 1/month | < 1/month |
| Lead Time for Changes | < 1 hour | < 1 day | < 1 week | > 1 month |
| Time to Restore Service | < 1 hour | < 1 day | < 1 week | > 1 week |
| Change Failure Rate | < 5% | < 10% | < 15% | > 15% |
Méthodologie
DevEx Audit en 5 phases
- Baseline — mesurer onboarding time, PR cycle time, build time
- Friction points — identifier pain points (sondage, interviews)
- Quick wins — automatiser tâches répétitives (scripts, pre-commit hooks)
- Platform engineering — internal developer platform (IDP)
- Metrics — dashboards DORA, developer satisfaction survey
Format d'amélioration DevEx
Pour chaque friction identifiée :
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.
- 8d ago First seen · 269 lines · 18 tokens per session scan A 759f56c2255e
devex-engineer is an agent published in the GitHub repository TheBeardedBearSAS/claude-craft (105 stars, last pushed 5d ago), licensed MIT. It adds 18 tokens to every session and 2,072 once invoked, about $0.0001 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 agents, from other repositories
ecosystem-specialist
Multi-language build, test, and lint specialist. Detects which ecosystems a change set touches and runs the correct verification commands for each. Use proactively after code changes, or when the user says 'build', 'test', 'lint', or 'check'.
Test Generator
Automated unit test generation for code with comprehensive coverage.
Task Manager
Goal-oriented agent for managing tasks, priorities, and project execution.
hybrid-cloud-architect
Expert hybrid cloud architect specializing in complex multi-cloud solutions across AWS/Azure/GCP and private clouds (OpenStack/VMware). Masters hybrid connectivity, workload placement optimization, edge computing, and cross-cloud automation. Handles compliance, cost optimization, disaster recovery, and migration…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.