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 sota-managementgit 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/sota-management)<a href="https://agentmods.dev/skills/katagiri-hoshino-lab/vibecodehpc/sota-management"><img src="https://agentmods.dev/badge/skills/katagiri-hoshino-lab/vibecodehpc/sota-management/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/sota-management"><img src="https://agentmods.dev/badge/skills/katagiri-hoshino-lab/vibecodehpc/sota-management.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 | $0.00026 | $0.00559 |
| Opus 5 | $0.00013 | $0.00280 |
| Sonnet 5 | $0.00005 | $0.00112 |
| Haiku 4.5 | $0.00003 | $0.00056 |
Grade A, and why
sota-management 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.
What it actually says
SOTA Management
Hierarchy
| Level | Scope | File | Manager |
|---|---|---|---|
| Local | PG directory best | sota_local.txt |
PG |
| Family | Same middleware parent-child | Virtual (from PG_visible_dir.md) | Auto |
| Hardware | Same hardware config | sota_hardware.txt |
SE |
| Project | Project-wide best | sota_project.txt |
PM |
Check Timing
- After PG records test performance in ChangeLog.md
- During SE/PM statistical analysis
Python API
${CLAUDE_SKILL_DIR}/scripts/sota_checker.py — checks and updates all 4 levels. Run with --help for usage.
Benefits
- Fast comparison via dedicated files (no ChangeLog scanning)
- Hierarchical isolation
- Family SOTA auto-computed from visibility scope
Details:
references/file_formats.md,references/sota_api.md
CLI Script
python3 ${CLAUDE_SKILL_DIR}/scripts/sota_checker.py --help
python3 ${CLAUDE_SKILL_DIR}/scripts/sota_checker.py /path/to/PG1.1 check "350.0 GFLOPS"
python3 ${CLAUDE_SKILL_DIR}/scripts/sota_checker.py /path/to/PG1.1 update "350.0 GFLOPS" --version 1.2.0 --agent PG1.1
python3 ${CLAUDE_SKILL_DIR}/scripts/sota_checker.py /path/to/PG1.1 info --json
Visualizer Script
scripts/sota_visualizer.py — self-contained SOTA visualization pipeline.
Generates 4-level graphs (local/family/hardware/project) from ChangeLog.md data.
Requires: matplotlib, numpy
# Pipeline mode (default, periodic execution)
python3 ${CLAUDE_SKILL_DIR}/scripts/sota_visualizer.py
# Debug mode (low DPI)
python3 ${CLAUDE_SKILL_DIR}/scripts/sota_visualizer.py --debug
# Summary only (no graph generation)
python3 ${CLAUDE_SKILL_DIR}/scripts/sota_visualizer.py --summary
# Data export for multi-project analysis
python3 ${CLAUDE_SKILL_DIR}/scripts/sota_visualizer.py --export
# Custom levels and DPI
python3 ${CLAUDE_SKILL_DIR}/scripts/sota_visualizer.py --levels local,project --dpi 80
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 63 lines · 26 tokens per session scan A 1afa038b579a
sota-management is a skill published in the GitHub repository Katagiri-Hoshino-Lab/VibeCodeHPC (39 stars, last pushed 5mo ago), licensed MIT. It adds 26 tokens to every session and 559 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.
bro
Restate the last message in plain human language, with no jargon.
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.