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 allemaar/open-skills --skill budget-checkgit clone --depth 1 https://github.com/allemaar/open-skillsWrote 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/allemaar/open-skills/budget-check)<a href="https://agentmods.dev/skills/allemaar/open-skills/budget-check"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/budget-check/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/allemaar/open-skills/budget-check"><img src="https://agentmods.dev/badge/skills/allemaar/open-skills/budget-check.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00112 | $0.01297 |
| Opus 5 | $0.00056 | $0.00648 |
| Sonnet 5 | $0.00022 | $0.00259 |
| Haiku 4.5 | $0.00011 | $0.00130 |
Grade A, and why
budget-check 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/budget-check
A pre-wave usage gate. Launching a multi-agent wave is the most expensive thing an agent does — N concurrent subagents, each burning tokens. /budget-check answers one question before you spend: is the current usage window close enough to its ceiling that starting a wave is reckless? It returns go, no-go, or unknown, and it fails closed — with no usage data it returns unknown, never a convenient "go".
It is deliberately small: a concrete wrapper around the public ccusage reader, not a judgment engine. It does not add a global rule or amend your operating directives — it is a skill you call, so the gate lives at the decision point, not as standing policy.
Structured execution spec:
protocol.yon. Read it for the canonical rules and step sequence; this file is explanation. The two must stay in sync — if you edit one, update the other and refresh the@STAMPdate.
The check — one tool, three verdicts
The skill ships references/tools/budget-check.mjs inside its own folder. Resolve the installed skill directory and run the bundled tool, which wraps ccusage blocks --json:
node <skill-dir>/references/tools/budget-check.mjs # go/no-go vs 95% of your historical-peak block
node <skill-dir>/references/tools/budget-check.mjs --threshold 90 # custom threshold (percent)
node <skill-dir>/references/tools/budget-check.mjs --token-limit 200000000 # explicit ceiling instead of the auto peak
node <skill-dir>/references/tools/budget-check.mjs --json # machine-readable verdict
- Ceiling =
--token-limit <N>if you pass one, else the largest historical (non-active) block's total tokens — ccusage's ownmaxnotion, i.e. "your usual peak window." Without--token-limit, the gate measures against your own historical peak — a relative signal ("am I near my personal worst window"), not your real plan budget. For a true budget gate, pass--token-limit <N>with your plan's actual token ceiling. - Verdict =
gowhen the active block is under the threshold,no-goat or over it,unknownwhen there is no usage data, no active block, or no ceiling to measure against. - Exit code =
0go ·1no-go ·2unknown — so a dispatch script can gate on it directly. - On no-go it also reports
secondsUntilWindowClearsand amin(3600, …)poll interval, so you know how long until the window resets.
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 · 70 lines · 112 tokens per session scan A 36804240bb9c
budget-check is a skill published in the GitHub repository allemaar/open-skills (14 stars, last pushed yesterday), licensed Apache-2.0. It adds 112 tokens to every session and 1,297 once invoked, about $0.0006 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
polis-protocol
Set up and run a self-improving, multi-vendor AI agent team with the Polis Protocol — a markdown polis/ folder where each agent is a citizen with a capability card, tasks are contracts routed to whoever has the best track record by a learning router, settled work files lessons that compound into team memory, and…
media
Skill "media" from ymxlx/polis-protocol, covering polis protocol: a self-optimizing city of agents, the core idea, when this skill is active, structure of a polis and the first thing to do every session.
_data
Skill "_data" from ymxlx/polis-protocol, covering polis protocol: a self-optimizing city of agents, the core idea, when this skill is active, structure of a polis and the first thing to do every session.
subagent-driven-development
Execute plans via delegatetask subagents (2-stage review).
mcporter
List, auth, and call MCP servers/tools from the terminal.
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.