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.
npx skills add rjmurillo/ai-agents --skill dx-reviewgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/rjmurillo/ai-agents/dx-review)<a href="https://agentmods.dev/skills/rjmurillo/ai-agents/dx-review"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/dx-review/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/rjmurillo/ai-agents/dx-review"><img src="https://agentmods.dev/badge/skills/rjmurillo/ai-agents/dx-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00130 | $0.03158 |
| Opus 5.5 | $0.00052 | $0.01263 |
| Sonnet 5.5 | $0.00026 | $0.00632 |
| Haiku 4.5 | $0.00013 | $0.00316 |
Grade A, and why
dx-review 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 22d 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 — 350 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dx-review: Evidence-Based Developer Experience Audit
You are a DX engineer dogfooding a developer product. You test the experience, not review a plan. Measure, do not guess.
Triggers
| Trigger Phrase | Operation |
|---|---|
run a DX audit |
Full audit of the target |
test the developer experience |
Full audit |
measure onboarding friction |
Full audit, emphasis on TTHW |
DX scorecard |
Full audit, emphasis on final scorecard |
evaluate developer ergonomics |
Full audit, emphasis on API/CLI |
Evidence Labels
Every score in the scorecard MUST cite one of these labels:
| Label | Meaning |
|---|---|
| TESTED | The auditor executed the interaction or command and observed the result |
| PARTIAL | Some aspects were executed and observed, others were inferred from artifacts |
| INFERRED | Concluded from static file or fetched documentation inspection only |
When a check involves interactive docs, forms, search, authentication, or web error paths, use browser tooling (e.g. computer use, browser MCP) when available. Fall back to WebFetch, WebSearch, or artifact inspection with PARTIAL or INFERRED evidence when browser tooling is unavailable. Fetched docs and search results alone are never TESTED. State what could not be tested and why.
Change-Scope Mode
/test Gate 5 invokes this skill in change-scope mode. It passes the
dx_trigger.py decision JSON, the changed paths, and the diff. Change-scope
mode audits only the developer journeys the change touches, not the whole
product. Every other rule in this skill still applies: evidence labels, command
safety, TTHW, and both blocking gates. Skip Step 0: the diff is the target.
When no user can approve a command (an unattended run), run no command, label
evidence PARTIAL or INFERRED, and set TTHW to N/A with that reason.
- Name the reviewed user journey: the concrete task a developer completes
through the changed surface, for example "install the plugin and run
/test". - Run the Process steps only for dimensions a changed journey can alter:
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.
- 22d ago Changed · +60 lines b00f35ff8710
- 1mo ago First seen · 290 lines · 130 tokens per session scan A 3318726b8ddc
dx-review is a skill published in the GitHub repository rjmurillo/ai-agents (48 stars, last pushed today), licensed MIT. It adds 130 tokens to every session and 3,158 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
install-gemini-code-review-action
Installs, configures, or upgrades Dazbo's PR code review & issue triage GitHub Action (gemini-review-action) in a target repository. Use when the user wants to set up, configure, or update automated AI code reviews, issue triaging, or Gemini model workflows for their GitHub repository.
review-deep
Review change vs spec, plan, code quality heuristics, and repo rules; append remediation phase if needed.
review-remote
Review open PR/MR and publish findings.
apply-review-feedback
Classify and apply accepted PR/MR review feedback.
azure-devops-automation
CI/CD pipelines, infrastructure as code, and deployment automation for Azure workloads.
architecture-audit
Comprehensive project consistency review across code, documentation, diagrams, and configuration.