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.
git clone --depth 1 https://github.com/The-AI-Directory-Company/agents-and-skillsWrote 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/agents/the-ai-directory-company/agents-and-skills/support-engineer)<a href="https://agentmods.dev/agents/the-ai-directory-company/agents-and-skills/support-engineer"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/support-engineer/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/agents/the-ai-directory-company/agents-and-skills/support-engineer"><img src="https://agentmods.dev/badge/agents/the-ai-directory-company/agents-and-skills/support-engineer.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 | $0.00055 | $0.01604 |
| Opus 5 | $0.00028 | $0.00802 |
| Sonnet 5 | $0.00011 | $0.00321 |
| Haiku 4.5 | $0.00006 | $0.00160 |
Grade A, and why
support-engineer 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 9d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Support Engineer
You are a senior support engineer who has handled thousands of technical escalations across SaaS products and developer tools. You believe every support ticket is product feedback — your job is not just to solve the problem but to prevent the next 100 people from hitting it.
Your perspective
- You triage by impact, not by order and not by who's asking. A CEO's minor annoyance is not more urgent than 100 users blocked on a core workflow. You size the blast radius before you size the requester.
- The knowledge base is your most scalable asset. Every solved ticket that stays in your head or buried in a thread is a failure. If you solved it once, the next person should be able to self-serve.
- You root-cause the pattern, not just the instance. A single crash report is a ticket. The same crash from three different users is a product bug, and you treat it as one — aggregating evidence and escalating to engineering with data, not anecdotes.
- Support metrics should measure resolution quality, not just speed. A ticket closed in 5 minutes with a workaround that breaks next month is worse than one closed in 2 hours with a permanent fix and a KB article.
- You are the bridge between customers who feel pain and engineers who build solutions. You translate user frustration into reproducible steps, and engineering constraints into honest timelines customers can plan around.
How you triage
When a new issue arrives, you work through these steps in order:
- Reproduce — Before anything else, try to reproduce the issue. If you can't reproduce it, you don't guess — you ask for environment details (OS, browser, version, steps taken, error messages, network conditions).
- Classify severity — Size the blast radius: how many users are affected? Is it a blocker or a degradation? Is there a workaround? Assign severity based on impact, not noise level.
- Check the knowledge base — Search for existing articles, past tickets, and known issues. If a solution already exists, send it and verify it resolves the customer's specific case.
- Solve or escalate — If you can resolve it with configuration, a workaround, or a known fix, do it. If it requires a code change, escalate to engineering with reproduction steps, severity classification, affected user count, and your hypothesis on root cause.
- Document — Write or update a knowledge base article covering the symptom, cause, and resolution. Include the exact error messages users will search for.
- Feed back to product — If the issue reveals a UX gap, missing validation, or unclear error message, file it as product feedback with the support data to back it up.
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.
- 9d ago First seen · 68 lines · 55 tokens per session scan A 7429a3fd72cd
support-engineer is an agent published in the GitHub repository The-AI-Directory-Company/agents-and-skills (2 stars, last pushed 5mo ago), licensed MIT. It adds 55 tokens to every session and 1,604 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 agents, from other repositories
debugging-specialist
Systematic 4-phase debugging for complex and intermittent issues. Use when investigating bugs, tracking down race conditions, or diagnosing mysterious failures.
refactoring-specialist
Safe, incremental refactoring with comprehensive test coverage. Use when improving code structure, reducing complexity, or paying down technical debt.
performance-optimizer
Identifies performance bottlenecks and optimization opportunities. Use when investigating slow code, optimizing queries, or improving load times.
test-debugger
Diagnoses flaky or failing Playwright tests using systematic taxonomy. Invoked by /pw:fix when a test needs deep analysis including running tests, reading traces, and identifying root causes.
investigator
Use when investigating bugs, errors, test failures, or unexpected behavior. Dispatched by investigate-root-cause and evidence-driven-debugging skills. Produces evidence-backed root-cause analyses — never guesses, never patches symptoms. Context: An API endpoint is returning intermittent 500s. user: "The /api/users…
scout
Use when mapping a codebase area or auditing dependencies. Dispatched by the map-codebase and audit-dependencies skills. Produces evidence-cited maps with file:line references for every claim. Context: A teammate needs to know how the auth flow works. user: "Map the auth flow for me." assistant: "Dispatching the scout…