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-step-fixWrote 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-step-fix)<a href="https://agentmods.dev/skills/easingthemes/dx-aem-flow/dx-step-fix"><img src="https://agentmods.dev/badge/skills/easingthemes/dx-aem-flow/dx-step-fix.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 7 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00051 | $0.03701 |
| Opus 5 | $0.00026 | $0.01851 |
| Sonnet 5 | $0.00010 | $0.00740 |
| Haiku 4.5 | $0.00005 | $0.00370 |
Grade A, and why
dx-step-fix 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You diagnose and fix issues that blocked a plan step — compilation errors, test failures, or review feedback. You try a direct fix first. If that fails, you escalate to creating corrective steps in implement.md for the step machinery to execute.
Use ultrathink for this skill — debugging requires deep reasoning about root causes.
Flow
digraph step_fix {
"Read blocked step from implement.md" [shape=box];
"Classify error" [shape=diamond];
"PERMANENT: Mark blocked, report" [shape=doublecircle];
"TRANSIENT: Suggest retry" [shape=doublecircle];
"Gather error context" [shape=box];
"Diagnose root cause" [shape=box];
"Load conventions" [shape=box];
"Apply fix" [shape=box];
"Re-verify (build/test)" [shape=box];
"Fix worked?" [shape=diamond];
"Mark step done + report" [shape=doublecircle];
"Fix failed — escalate to heal?" [shape=diamond];
"Determine failure type" [shape=diamond];
"Analyze blocked step with different approach" [shape=box];
"Group review issues by file cluster" [shape=box];
"Create corrective steps in implement.md" [shape=box];
"Corrective steps viable?" [shape=diamond];
"Return: healed (new steps)" [shape=doublecircle];
"Return: unrecoverable" [shape=doublecircle];
"Read blocked step from implement.md" -> "Classify error";
"Classify error" -> "PERMANENT: Mark blocked, report" [label="PERMANENT"];
"Classify error" -> "TRANSIENT: Suggest retry" [label="TRANSIENT"];
"Classify error" -> "Gather error context" [label="VALIDATION"];
"Gather error context" -> "Diagnose root cause";
"Diagnose root cause" -> "Load conventions";
"Load conventions" -> "Apply fix";
"Apply fix" -> "Re-verify (build/test)";
"Re-verify (build/test)" -> "Fix worked?";
"Fix worked?" -> "Mark step done + report" [label="yes"];
"Fix worked?" -> "Fix failed — escalate to heal?" [label="no"];
"Fix failed — escalate to heal?" -> "Return: unrecoverable" [label="no (environment/config)"];
"Fix failed — escalate to heal?" -> "Determine failure type" [label="yes"];
"Determine failure type" -> "Analyze blocked step with different approach" [label="step-blocked"];
"Determine failure type" -> "Group review issues by file cluster" [label="review-failed"];
"Analyze blocked step with different approach" -> "Corrective steps viable?";
"Group review issues by file cluster" -> "Create corrective steps in implement.md";
"Create corrective steps in implement.md" -> "Corrective steps viable?";
"Corrective steps viable?" -> "Return: healed (new steps)" [label="yes"];
"Corrective steps viable?" -> "Return: unrecoverable" [label="no"];
}
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 · 347 lines · 51 tokens per session scan A 363668bef151
dx-step-fix is a skill published in the GitHub repository easingthemes/dx-aem-flow (6 stars, last pushed 6d ago), licensed MIT. It adds 51 tokens to every session and 3,701 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
testing
Skill validation framework PLUS daily test-suite health and regression intelligence. Validates skill conformance (frontmatter, manifest coverage, resolver coverage). Runs the project test suite in tiered phases (unit / evals / integration / system health), classifies failures, and produces a regression-aware report.
verify
Verify that a change really works before you claim completion.
detect-static-dependencies
Scan C# source files for hard-to-test static dependencies — DateTime.Now/UtcNow, File., Directory., Environment., HttpClient, Console., Process., and other untestable statics. Produces a ranked report of static call sites by frequency. USE FOR: find untestable statics, scan for static dependencies, testability audit…
experiment-iterative-coder
Iterative code refinement through plan → code → evaluate → refine cycles. Runs lint checks (ruff), tests (pytest), and structured self-evaluation each cycle, then diagnoses failures and refines. Decomposes complex tasks into sequential phases, iterates up to 3 times per phase (10 total). Use when: the main agent…
testing-blocks
Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.
symbolic-execution-assistant
Performs symbolic execution to detect potential errors by exploring execution paths, solving path constraints, and generating test inputs. Use when you need to analyze code for bugs like null dereferences, division by zero, buffer overflows, or assertion violations. Also use to generate test inputs that exercise…