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 budget-trackinggit 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/budget-tracking)<a href="https://agentmods.dev/skills/katagiri-hoshino-lab/vibecodehpc/budget-tracking"><img src="https://agentmods.dev/badge/skills/katagiri-hoshino-lab/vibecodehpc/budget-tracking/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/budget-tracking"><img src="https://agentmods.dev/badge/skills/katagiri-hoshino-lab/vibecodehpc/budget-tracking.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 | $0.00502 |
| Opus 5 | $0.00014 | $0.00251 |
| Sonnet 5 | $0.00005 | $0.00100 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
budget-tracking 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
Budget Tracking
Phases
| Phase | Range | Action |
|---|---|---|
| 0 | 0 — minimum | Verify basic operation, fix environment issues |
| 1 | — 50% of target | Aggressive exploration, broad parameter search |
| 2 | 50-80% | Focus on promising approaches, cost-efficiency |
| 3 | 80-100% of target | Best optimization only, start summarizing |
| 4 | target — 90% of deadline | Pre-approve new jobs, prepare final report |
| 5 | 90-100% of deadline | No new jobs, terminate all work within 5 min |
Budget Thresholds (set in requirement_definition.md)
- Minimum: Basic verification budget
- Target: Expected optimization budget
- Deadline: Absolute maximum
Consumption Formula
project_usage = current_used - start_used
consumption_% = (project_usage / deadline) × 100
Note: used is cumulative annual value — always diff from project start.
Critical Rules
- Login node execution is forbidden (policy violation)
- Zero point consumption → warn agent immediately
- Budget check commands are supercomputer-specific (see
_remote_info/)
Details:
references/phase_details.md
Operational Notes
determine_phase()is called automatically bysummarise()and included in--summaryoutput.- Phase is computed from
DEFAULT_BUDGET_LIMITSkeys: Minimum, Expected (target), Deadline. - Agents should check phase before submitting new jobs and adjust strategy accordingly.
CLI Script
python3 ${CLAUDE_SKILL_DIR}/scripts/budget_tracker.py --help
python3 ${CLAUDE_SKILL_DIR}/scripts/budget_tracker.py /path/to/project --summary
python3 ${CLAUDE_SKILL_DIR}/scripts/budget_tracker.py /path/to/project --report --json
python3 ${CLAUDE_SKILL_DIR}/scripts/budget_tracker.py /path/to/project --jobs --json
python3 ${CLAUDE_SKILL_DIR}/scripts/budget_tracker.py /path/to/project --visualize -o budget.png
What ships with it
2 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.
- 11d ago First seen · 52 lines · 27 tokens per session scan A 6c6fdb35828d
budget-tracking is a skill published in the GitHub repository Katagiri-Hoshino-Lab/VibeCodeHPC (39 stars, last pushed 5mo ago), licensed MIT. It adds 27 tokens to every session and 502 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
pipa-budget-setup
Use only when pipa-budget-setup is explicitly invoked or pipa-get-paid delegates to it. Do not trigger from generic language.
close-management
Manage the month-end close process with task sequencing, dependencies, and status tracking. Use when planning the close calendar, tracking close progress, identifying blockers, or sequencing close activities by day.
omc-plan
Strategic planning with optional interview workflow.
project-session-manager
Worktree-first dev environment manager for issues, PRs, and features with optional tmux sessions.
ask-navigator
Shipyard's navigator — chart a foggy effort (destination unclear, questions not yet stateable) into a map of decision tickets on the repo's issue tracker, then work the frontier one ticket per session until the way is clear, and hand the collapsed decisions to /launch as a mission brief. Wayfinding, not building: it…
ultragoal
Durable multi-goal workflow that persists plan/ledger artifacts under .omc/ultragoal and prints Claude /goal handoff text for the active session.