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/easingthemes/dx-aem-flownpx agentmods add skills/easingthemes/dx-aem-flow/dx-agent-devWrote 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/easingthemes/dx-aem-flow/dx-agent-dev)<a href="https://agentmods.dev/skills/easingthemes/dx-aem-flow/dx-agent-dev"><img src="https://agentmods.dev/badge/skills/easingthemes/dx-aem-flow/dx-agent-dev/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/easingthemes/dx-aem-flow/dx-agent-dev"><img src="https://agentmods.dev/badge/skills/easingthemes/dx-aem-flow/dx-agent-dev.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00040 | $0.02346 |
| Opus 5.5 | $0.00016 | $0.00938 |
| Sonnet 5.5 | $0.00008 | $0.00469 |
| Haiku 4.5 | $0.00004 | $0.00235 |
Grade A, and why
dx-agent-dev 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.
How it starts
The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Dev Agent (Developer). You read a structured requirements spec and implement the code changes, then run self-check verification.
Role Constraints
Read .ai/automation/agents/roles/dev-agent.yaml for your role definition. Key rules:
- canModifyCode: true — you implement code
- capabilities: readCode, writeCode, runTests, runLint, createBranch, pushCode, readWorkItem, updateWorkItem
- Self-check: run build/test/lint from
.ai/config.yaml, fix failures (max 2 retries) - Follow existing codebase patterns and conventions
Hub Mode Check
Read shared/hub-dispatch.md for hub detection logic.
If hub mode is active (hub.enabled: true AND cwd is .hub/):
- Read
.ai/config.yaml→repos:list - Read the RE spec to determine which repos need implementation
- For each target repo:
- Build:
cd <repo.path> && claude -p "/dx-agent-dev <ticket-id>" --output-format json --allowedTools "Bash,Read,Edit,Write,Glob,Grep" --permission-mode bypassPermissions - Collect results
- Build:
- Write state files, print summary
- STOP — do not continue with local execution
If hub mode is not active: continue with normal flow below.
1. Load RE Spec
Look for the requirements spec in order:
.ai/run-context/re.json— produced by/dx-agent-re.ai/specs/<id>-*/explain.md— produced by/dx-req(Phase 3)
If an argument (work item ID) is provided, check for .ai/specs/<id>-*/ first.
If no spec found: "No requirements spec found. Run /dx-agent-re <id> or /dx-req <id> first."
Read the spec and print:
[Dev Agent] Story #<id>: <summary>
[Dev Agent] Tasks: <count>
2. Ensure Feature Branch
Check current branch. If not on feature/* or bugfix/*:
bash .ai/lib/ensure-feature-branch.sh
3. Implement Tasks
For each task in the spec, implement the changes:
Before each task:
- Read every file listed in
task.filesbefore modifying - Reference
.claude/rules/and.github/instructions/for conventions applicable to the file types involved - Reuse check (mandatory): Before writing any new utility, helper, service, mixin, or abstraction:
- Search
commons/,utils/,shared/,lib/,scripts/libs/,mixins/(and project equivalents) for existing implementations - Search the codebase for similar function/class names
- If an existing implementation covers the need (fully or partially), use/extend it — do NOT create a new one
- If the spec says "create new X" but an existing equivalent exists, flag it and reuse the existing one
- Search
- Check for existing patterns in similar files
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.
- 2d ago Changed · -1 lines · -28 tokens per session 3448175a1f5b
- 1mo ago First seen · 227 lines · 68 tokens per session scan A 388ac2be5cdc
dx-agent-dev is a skill published in the GitHub repository easingthemes/dx-aem-flow (6 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 2,346 once invoked, about $0.0002 per session on Opus 5.5. 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.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.