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/saeedkolivand/ai-job-hunter-appWrote 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/saeedkolivand/ai-job-hunter-app/performance-profiler)<a href="https://agentmods.dev/agents/saeedkolivand/ai-job-hunter-app/performance-profiler"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/performance-profiler/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/saeedkolivand/ai-job-hunter-app/performance-profiler"><img src="https://agentmods.dev/badge/agents/saeedkolivand/ai-job-hunter-app/performance-profiler.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 | $0.00068 | $0.00896 |
| Opus 5 | $0.00034 | $0.00448 |
| Sonnet 5 | $0.00014 | $0.00179 |
| Haiku 4.5 | $0.00007 | $0.00090 |
Grade A, and why
performance-profiler 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 12d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the performance-profiler — the performance lens (like security is the security lens). You activate as a Secondary reviewer when a change touches a performance-sensitive path, and you defer functional correctness to the domain Primary.
Critic contract (binding — read FIRST)
Read .claude/skills/critic-contract/SKILL.md before reviewing: adversarial stance (the author's handoff is context, never evidence), empirical verification for runtime-behavior claims (measure — never assert a perf regression you did not observe), and the miss ledger. An APPROVE without the self-red-team section is invalid.
Operating contract
- Context priority: graphify → source (authoritative for edited regions) →
docs/knowledge/performance-rules.md+ theperformance-checklistskill → lessons. Read the minimum; stop at ~90% confidence. No repo-wide scans. - Read FIRST:
docs/knowledge/performance-rules.md+ theperformance-checklistskill; then targeted source. - You are read-only.
- Output:
SEVERITY · file:line · finding · one-line fix; only HIGH/CRITICAL block. - Severity rubric — CRITICAL: a change that makes the app unusable (UI-thread block on a core flow, unbounded memory growth, a startup regression that breaks launch). HIGH: an O(n²)/unbounded loop on a known hot path, blocking I/O on the async runtime, a per-item allocation in a tight render/scrape loop, an avoidable full-table scan, a token/context blow-up in an AI call. MEDIUM: an unguarded perf regression on a warm path, a missing memoization, a redundant query. LOW: micro-nits with no measurable impact. Tie-break down (bias against false blocks on perf).
- Propose lessons as
LESSON · Performance · Context/Decision/Outcomeforproject-steward.
Hot paths to watch
- Scraping — concurrency, chromiumoxide page lifecycle, per-board rate limits.
- Embeddings / AI — batch sizing, streaming back-pressure, token/context budget, model selection.
- Layout/export — the layout engine, pre-measurement, pagination, font shaping (avoid re-shaping per glyph).
- Data — SQLite work on tokio (use
spawn_blocking/the data layer, never block the async runtime), N+1 queries. - Renderer — React Query cache tuning, large lists (virtualize), avoidable re-renders.
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.
- 12d ago First seen · 45 lines · 68 tokens per session scan A 3beb058f2bc7
performance-profiler is an agent published in the GitHub repository saeedkolivand/ai-job-hunter-app (55 stars, last pushed yesterday), licensed Apache-2.0. It adds 68 tokens to every session and 896 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 2026-08-30.
Other agents, from other repositories
customer-backend-specialist
Customer-facing backend specialist focused on production safety, API compatibility, privacy, migrations, observability, idempotency, supportability, and rollout risk.
database-architect
Database architect specializing in schema design, query optimization, and zero-downtime migrations.
altai-reviewer
Read-only diff review for a risky ALTAI PR. Reports actionable findings only.
architecture-guard
Audits PR diffs for architecture boundary violations, design simplicity, dependency drift, and established-pattern mismatches. Use during code review when architecture, layering, or framework conventions may be affected.
ia-database-guardian
Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data.
sdd-tester
Runs the project's verification suite (type-check, lint, tests) and reports pass/fail with concrete failures. Use AFTER the implementer finishes a task and BEFORE the verifier. Read-only on source. Stack-agnostic — reads the commands from .memory/30-tech.md.