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/auto-testWrote 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/auto-test)<a href="https://agentmods.dev/skills/easingthemes/dx-aem-flow/auto-test"><img src="https://agentmods.dev/badge/skills/easingthemes/dx-aem-flow/auto-test/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/auto-test"><img src="https://agentmods.dev/badge/skills/easingthemes/dx-aem-flow/auto-test.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 | $0.00052 | $0.01769 |
| Opus 5.5 | $0.00021 | $0.00708 |
| Sonnet 5.5 | $0.00010 | $0.00354 |
| Haiku 4.5 | $0.00005 | $0.00177 |
Grade A, and why
auto-test 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 — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You run an AI automation agent locally against real ADO data. With --dryRun, results are logged but nothing is posted to ADO or committed. Without --dryRun, the agent runs fully (posts comments, applies fixes).
0. Prerequisites
Check required env vars are set (in shell or .claude/settings.local.json):
ANTHROPIC_API_KEY- ADO MCP authenticated (browser OAuth) or
ADO_MCP_AUTH_TOKENset
1. Parse Arguments
From the user's command:
- Agent:
dor,dod,dod-fix,pr-review,pr-answer,bugfix,qa,devagent,docagent, orestimation - Target ID: work item ID (dor) or PR ID (pr-review, pr-answer)
- Repo name (pr-review, pr-answer)
--dryRunflag: defaulttruefor safety
If no arguments: Read .ai/automation/infra.json to get automationProfile and the list of enabled agents (those without "disabled": true). Then prompt with only the enabled agents:
Which agent to test?
Only show agents that are enabled for this profile:
- consumer (or legacy
pr-only/pr-delegation): PR Review, PR Answer, DevAgent, BugFix, DoD Fix - full-hub: all agents
Full agent list (filter to enabled):
- DoR — needs work item ID
- DoD — needs work item ID
- DoD Fix — needs work item ID
- PR Review — needs PR ID + repo name
- PR Answer — needs PR ID + repo name
- BugFix — needs Bug work item ID
- QA — needs work item ID
- DevAgent — needs work item ID (User Story)
- DOCAgent — needs work item ID (User Story)
- Estimation — needs work item ID
If the user requests an agent that is disabled for this profile, report: ⚠ <agent> is not enabled for the <profile> profile. To enable it, re-run /auto-init.
Target ID? (work item ID or PR ID)
Dry run? (default: yes — log results without posting to ADO)
- Yes — dry run (recommended for first test)
- No — live run (posts real comments/applies fixes)
2. Run Agent
node .ai/automation/scripts/pipeline-agent.js "<skill-prompt>"
Map agent names to skill prompts:
| Agent | Skill Prompt |
|---|---|
| dor | /dx-req-dod <id> |
| dod | /dx-req-dod <id> |
| dod-fix | /dx-req-dod <id> |
| pr-review | /dx-pr-review <pr-url> analyze only (dry run) or /dx-pr-review <pr-url> (live) |
| pr-answer | /dx-pr-answer <pr-url> |
| bugfix | /dx-bug-all <id> |
| devagent | /dx-agent-all <id> |
| docagent | /dx-doc-gen <id> |
| estimation | /dx-estimate <id> |
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 1b6d31f9e4f5
- 1mo ago First seen · 145 lines · 52 tokens per session scan A 6d39e43ed64d
auto-test is a skill published in the GitHub repository easingthemes/dx-aem-flow (6 stars, last pushed 2d ago), licensed MIT. It adds 52 tokens to every session and 1,769 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.