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 frankxai/claude-skills-library --skill context-budgetgit clone --depth 1 https://github.com/frankxai/claude-skills-libraryWrote 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/frankxai/claude-skills-library/context-budget)<a href="https://agentmods.dev/skills/frankxai/claude-skills-library/context-budget"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/context-budget/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/frankxai/claude-skills-library/context-budget"><img src="https://agentmods.dev/badge/skills/frankxai/claude-skills-library/context-budget.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 | $0.00041 | $0.00412 |
| Opus 5.5 | $0.00016 | $0.00165 |
| Sonnet 5.5 | $0.00008 | $0.00082 |
| Haiku 4.5 | $0.00004 | $0.00041 |
Grade A, and why
context-budget 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 17d 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
Context budget for this estate
A skill that sits in the default prompt costs tokens on every turn. A skill that loads only when its description matches does not. Measure the default prompt before you add anything.
Caps already in force
- Turn-0 skill listing stays near 8,000 tokens. A listing near 18,000 is over budget.
- Skill Foundry on 2026-10-09 counted 402 Claude skills and 380 with no invocation in 30 days. Retirement of those skills is Frank's decision. Until then, new skills stay cold.
- A new skill enters the default prompt only after it has a saved eval.
- Enabled MCP servers stay under 10. Tool count stays under 80. A server that only wraps
gh,vercel, ornpxshould be a CLI call. - Keep a docs tool such as Context7. Leave Higgsfield disabled.
- The continuous-learning observer stays off until the unused skills are retired. An observer that promotes new skills into the prompt makes the budget worse.
What to report
- Servers enabled, and the tool count.
- Skills in the default prompt, and skills that have an eval.
- The one removal that frees the most tools.
- Whether the thing you wanted to add already exists under
starlight/repos.
Do not install a token-proxy product as part of this audit.
Where this came from
The inventory idea follows affaan-m/ECC skills/context-budget at 4eb71d92a39cab44ad40ac9d8a6a5ccb4029d6c2 (MIT). The caps, the Foundry counts, and the cold-skill rule are estate measurements.
Built on SIP.
What ships with it
1 file 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.
- 17d ago First seen · 34 lines · 41 tokens per session scan A 577ece781c0c
context-budget is a skill published in the GitHub repository frankxai/claude-skills-library (47 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 412 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-11.
Other skills, from other repositories
token-saver
Token optimization guide for Claude Code. This skill should be used when the user wants to reduce API costs, learn model routing strategies, or understand how to use free/cheaper tools (Ollama, Haiku) instead of burning expensive Claude tokens on routine tasks. Triggers on: save tokens, reduce costs, token tips, cheap…
wayfinder
A planning method that maps a large, uncertain project into linked decision tickets in a repository's issue tracker. An issue tracker is a system for recording and organizing project work.
scaffold-exercises
A directory scaffold for course exercises, with sections, exercise folders, and optional problem, solution, or explanation versions. It creates the required Markdown files and checks the result with the repository's linter.
migrate-to-shoehorn
A testing guide for Shoehorn, a TypeScript library that lets tests provide only the fields they need from a larger data type.
ask-matt
A skill router that helps choose the right workflow or skill for the current task. It maps work from an initial idea through building and shipping, with separate paths for research, prototypes, and multi-session projects.
improve-codebase-architecture
A skill that scans a codebase for places where restructuring could make future changes and testing easier, then produces an HTML report for selected improvements.