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 skills add Katagiri-Hoshino-Lab/VibeCodeHPC --skill performance-reportgit clone --depth 1 https://github.com/Katagiri-Hoshino-Lab/VibeCodeHPCWrote 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/skills/katagiri-hoshino-lab/vibecodehpc/performance-report)<a href="https://agentmods.dev/skills/katagiri-hoshino-lab/vibecodehpc/performance-report"><img src="https://agentmods.dev/badge/skills/katagiri-hoshino-lab/vibecodehpc/performance-report/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/skills/katagiri-hoshino-lab/vibecodehpc/performance-report"><img src="https://agentmods.dev/badge/skills/katagiri-hoshino-lab/vibecodehpc/performance-report.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 | $0.00024 | $0.00227 |
| Opus 5 | $0.00012 | $0.00113 |
| Sonnet 5 | $0.00005 | $0.00045 |
| Haiku 4.5 | $0.00002 | $0.00023 |
Grade A, and why
performance-report 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 11d 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.
What it actually says
Report Hierarchy
Three Tiers
| Tier | Format | Author | Location |
|---|---|---|---|
| Primary | ChangeLog.md | PG (auto) | Each PG directory |
| Secondary | Markdown + graphs | SE (semi-auto) | User-shared/reports/ |
| Final | Executive summary | PM | User-shared/final_report.md |
Directory Layout
Agent-shared/ # Technical tools (agents only)
User-shared/ # Deliverables (user-facing)
├── final_report.md
├── reports/
└── visualizations/
Timing
- Primary: PG records after every code change
- Secondary: SE generates at milestones
- Final: PM creates at project end (includes ROI, budget summary, recommendations)
Rules
- Update existing reports — never create duplicates
- Final report must state achievement as % of theoretical peak
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.
- 11d ago First seen · 33 lines · 24 tokens per session scan A 4fa38d73c3be
performance-report is a skill published in the GitHub repository Katagiri-Hoshino-Lab/VibeCodeHPC (39 stars, last pushed 5mo ago), licensed MIT. It adds 24 tokens to every session and 227 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 skills, from other repositories
codeman
Drive Codeman, the session manager this agent is running inside, over its HTTP API: list sessions, start worker sessions, send them prompts, block until they finish (wait / wait-output / send-and-wait), read their output, and clean up; where available, message claude workers directly (Claude Code cross-session…
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
southwest
Search Southwest Airlines fares and points pricing via Patchright browser automation. SW is not in any GDS or API. Covers all fare classes, Companion Pass value, and fare drop monitoring.
points-valuations
Cents-per-point (cpp) valuations across major loyalty programs from four publications. Floor/ceiling rules for deciding if a redemption is good or exceptional.
bro
Restate the last message in plain human language, with no jargon.