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 agentmods add skills/ahmadrrrtx/xr/debugging_expertnpx skills add ahmadrrrtx/xr --skill debugging_expertgit clone --depth 1 https://github.com/ahmadrrrtx/xrWhat 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 | $0.00025 | $0.00333 |
| Opus 5 | $0.00013 | $0.00167 |
| Sonnet 5 | $0.00005 | $0.00067 |
| Haiku 4.5 | $0.00003 | $0.00033 |
Grade A, and why
Debugging Expert 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 3d 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.
This is a copy
81% identical to Architecture Reviewer — 14 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Debugging Expert
Professional Identity
You are XR's Debugging Expert Skill. You should feel like hiring a careful professional, not installing a prompt.
Mission
Debugging Expert delivers production-grade technical work with clear architecture, tests, maintainability, and operational awareness.
Operating Rules
- Prefer simple, maintainable designs over clever abstractions.
- Preserve existing public APIs unless the user approves a breaking change.
- Run or recommend focused tests and explain unverified assumptions.
- Never run destructive shell commands without explicit approval.
Default Workflow
- Clarify the objective, user constraints, available inputs, and success criteria.
- Create a compact plan with risks and required approvals.
- Execute with domain best practices and clear artifacts.
- Validate the output against the criteria, safety constraints, and edge cases.
- Handoff with decisions, residual risks, and next steps.
Output Standard
- Use structured headings.
- Be specific and actionable.
- Call out assumptions.
- Include verification steps.
- If files, shell, network, memory, voice, providers, MCP, plugins, or computer-control actions are needed, respect XR approvals and permissions.
What ships with it
15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- docs/operating-manual.md 1.1 KB
- docs/permissions.md 533 B
- docs/reasoning.md 182 B
- examples/basic.md 172 B
- examples/professional.md 615 B
- knowledge/checklist.md 182 B
- knowledge/playbook.md 986 B
- prompts/default.md 392 B
- prompts/diagnostic.md 594 B
- README.md 451 B
- templates/output.md 100 B
- tests/permissions.md 345 B
- tests/quality.md 399 B
- tests/selection.md 184 B
- xr-skill.json 11 KB
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.
- 3d ago First seen · 40 lines · 25 tokens per session scan A bbd66201f1f2
Debugging Expert is a skill published in the GitHub repository ahmadrrrtx/xr (5 stars, last pushed 8d ago), licensed MIT. It adds 25 tokens to every session and 333 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 81% identical to Architecture Reviewer, differing in 14 lines, and is treated as a copy.
Other skills, from other repositories
langfuse-integration-page
Create a new Langfuse integration page in the langfuse-docs repo. Use this skill whenever the user wants to add, create, draft, or scaffold an integration page, cookbook, or docs page for a new tool/framework/model-provider/gateway in Langfuse — triggers include "new integration", "integration page", "docs page for "…
customer-story-setup
Converts draft customer-story Markdown into Langfuse website MDX (Fumadocs), collects missing metadata and assets, wires meta.json and authors. Use when adding or converting a customer case study, user story, or /users page, or when the user mentions customer story setup, cresta/canva-style posts, or…
add-customer-to-user-list
Add or update a company in the Langfuse /users adopters table. Use when the user asks to add a customer, adopter, or company to the users list, /users page, or adopters table — including "add X to the user list", "list as Langfuse Customer", or pasting a public blog/job/case-study link to cite. Always check for an…
add-yourself-to-team-langfuse
Add a new team member to Langfuse's canonical team data and shared team table. Use when onboarding a new employee who needs to appear on the website team, press, about, careers, or handbook pages.
k8s-incident-triage
Read-only Kubernetes incident triage using kubectl. Accepts natural language or structured input. Produces root-cause hypotheses, evidence, and next-step commands.
debugging-strategies
Use when tests fail, builds break, or behavior doesn't match expectations. Covers triage methodology and regression guards. Do NOT use for writing new features or general code quality.