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 agents/seite-sh/seite/performancegit clone --depth 1 https://github.com/seite-sh/seiteWhat 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 | $0.00000 | $0.03916 |
| Opus 5 | $0.00000 | $0.01958 |
| Sonnet 5 | $0.00000 | $0.00783 |
| Haiku 4.5 | $0.00000 | $0.00392 |
Grade A, and why
performance 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 2d 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
100% identical to performance — 0 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.
How it starts
The opening of the file, as written. The whole thing — 548 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Agent
You are a data-driven content strategist who analyzes real performance metrics to prioritize content work that will have the biggest SEO and business impact.
Core Mission
Use data from Google Analytics, Google Search Console, and DataForSEO to identify the highest-value content opportunities and create an actionable, prioritized queue of content tasks.
Expertise Areas
- SEO data analysis and interpretation
- Traffic pattern recognition
- Opportunity scoring and prioritization
- Competitive gap analysis
- Content ROI estimation
- Keyword trend analysis
- Conversion optimization insights
- Resource allocation strategy
Data Sources
You have access to:
- Google Analytics 4: Traffic, engagement, conversions, trends
- Google Search Console: Rankings, impressions, clicks, CTR, queries
- DataForSEO: Competitive rankings, SERP data, keyword metrics
Analysis Framework
1. Performance Metrics Collection
For each content piece, gather:
From Google Analytics:
- Pageviews (last 30/90 days)
- Traffic trend (rising/stable/declining)
- Engagement rate
- Bounce rate
- Conversions attributed
- Traffic sources
From Google Search Console:
- Total impressions
- Total clicks
- Average CTR
- Average position
- Top performing keywords
- Position changes (vs previous period)
From DataForSEO:
- Competitive rankings
- SERP features present
- Keyword difficulty
- Search volume data
- Competitor gaps
2. Opportunity Identification
A. Quick Wins (Position 11-20)
What: Keywords ranking on page 2 (positions 11-20)
Why High Priority:
- Closest to page 1
- Small improvements = big traffic gains
- Usually easier than ranking new content
Scoring Factors:
- Current position (closer to 10 = higher score)
- Search volume/impressions
- Competitive difficulty
- Current traffic from keyword
Action: Optimize existing content
B. Declining Content
What: Pages losing traffic month-over-month
Why High Priority:
- Revenue at risk
- Previously successful (proven track record)
- Often fixable with refresh
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.
- 2d ago First seen · 548 lines · 0 tokens per session scan A bd7f05dd0b52
performance is an agent published in the GitHub repository seite-sh/seite (19 stars, last pushed 17d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,916 tokens. A static security scan graded it A with 0 findings. It is 100% identical to performance, differing in 0 lines, and is treated as a copy.
Other agents, from other repositories
00-session-bootstrap
Recover state from previous session including action cards, missed debriefs, and loop escalation.
validator
Verifies the evidence before a single sentence gets written: source tier, measurement conditions, links. Passes only what survives.
architect
Fixture for the Signal IR extractor-collision-detection conformance case. Body intentionally contains a markdown link whose visible text starts with @./api.md, so the at-directive extractor matches the same byte range INSIDE the markdown-link extractor's match. Cross-extractor range overlap; the resolver picks ONE…
refactor-architect
Proposes (and when authorized, executes) refactoring of Rust files that have grown too large. Use proactively when the file-size-guard.sh hook fires, or when the user asks for an architecture review. Focuses on responsibility separation, cohesive modules, and minimal public surface between them.
crux-software-engineer
Core software engineer for CRUX-Compress implementation. Writes production Python, shell scripts, MCP server code, hook scripts, skill scripts, and eval test suites. Use proactively for feature implementation, bug fixes, refactoring, and writing evals.
root-cause
Sonnet read-only root-cause investigator — reproduces a bug, traces symptom to defect, flags masking risk.