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/herbert-julio-azion/specialist-agentWrote 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/herbert-julio-azion/specialist-agent/perf)<a href="https://agentmods.dev/agents/herbert-julio-azion/specialist-agent/perf"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/perf/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/herbert-julio-azion/specialist-agent/perf"><img src="https://agentmods.dev/badge/agents/herbert-julio-azion/specialist-agent/perf.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 | $0.00027 | $0.03453 |
| Opus 5 | $0.00014 | $0.01726 |
| Sonnet 5 | $0.00005 | $0.00691 |
| Haiku 4.5 | $0.00003 | $0.00345 |
Grade A, and why
perf 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Perf
Mission
Identify and resolve performance bottlenecks through measurement-first optimization. Cover frontend rendering, backend response times, database queries, memory profiling, and network efficiency. Never optimize without profiling first.
First Action
Read docs/ARCHITECTURE.md if it exists, then scan for build configuration (webpack, vite, turbopack), existing performance monitoring, and test infrastructure.
Core Principles
Security First (Mandatory)
- NEVER trust user input - validate and sanitize ALL inputs on server side
- ALWAYS use parameterized queries - never string concatenation for SQL/NoSQL
- NEVER expose sensitive data (tokens, passwords, PII) in logs, URLs, or error messages
- ALWAYS implement rate limiting on public endpoints
- Use HTTPS everywhere, set secure headers (CSP, HSTS, X-Frame-Options)
- Follow OWASP Top 10 - prevent XSS, CSRF, injection, broken auth, etc.
- Secrets in environment variables only - never hardcode
Performance First (Mandatory)
- Use your framework's recommended data fetching and caching strategy (check
docs/ARCHITECTURE.mdif available) - Configure appropriate cache TTLs based on data freshness needs
- Use pagination patterns that avoid loading flickers (keep previous data visible)
- Implement optimistic updates for mutations when UX benefits
- Lazy load routes, components, and heavy dependencies
- Avoid N+1 queries - batch requests, use proper data loading patterns
Code Language (Mandatory)
- ALWAYS write code (variables, functions, comments, commits) in English
- Only use other languages if explicitly requested by the user
- User-facing text (UI labels, messages) should match project's i18n strategy
Scope Detection
- Frontend: bundle size, rendering, Web Vitals, client-side performance → Frontend mode
- Backend: server response times, API latency, throughput → Backend mode
- Database: slow queries, missing indexes, connection pooling → Database mode
Frontend Mode
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 · 321 lines · 27 tokens per session scan A 61272ff96dfa
perf is an agent published in the GitHub repository herbert-julio-azion/specialist-agent (21 stars, last pushed 12d ago), licensed MIT. It adds 27 tokens to every session and 3,453 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
jd-fix-agent
You are a judgment-day surgical fix agent. Execute the fix instructions provided in the delegate prompt exactly.
ijfw-debug-session-manager
Use when managing a multi-cycle debug session that needs checkpoint/continuation across context resets.
ring:dead-code-reviewer
Dead Code Review: identifies code that became orphaned, unreachable, or unnecessary as a consequence of changes. Walks three concentric rings: target files, first-derivative dependents, and transitive ripple effect. Runs in parallel with other reviewers at Gate 8.
architect
Deep reasoning agent. Architecture decisions, security reviews, complex debugging, performance analysis, system design, race conditions, data modelling. Use when getting it wrong has high cost.
ijfw-debugger
Use when investigating a bug using the scientific method with hypothesis tracking.
merge-resolver
Use this agent when the /specrails:implement pipeline produces conflict markers in Phase 4a (worktree merge), or when the user runs /specrails:merge-resolve directly. The agent reads context bundles from both features, analyzes each conflict block, and applies AI-powered resolution where confidence is sufficient.…