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 ericrisco/rsc-harness --skill context-budgetgit clone --depth 1 https://github.com/ericrisco/rsc-harnessWrote 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/ericrisco/rsc-harness/context-budget)<a href="https://agentmods.dev/skills/ericrisco/rsc-harness/context-budget"><img src="https://agentmods.dev/badge/skills/ericrisco/rsc-harness/context-budget.svg" alt="Measured on agentmods" 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 | $0.00082 | $0.02340 |
| Opus 5 | $0.00041 | $0.01170 |
| Sonnet 5 | $0.00016 | $0.00468 |
| Haiku 4.5 | $0.00008 | $0.00234 |
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 8d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context budget
The context window is RAM, not a hard drive. Full ≠ free: a window stuffed to 95% does not just cost more money, it reasons worse. Model performance degrades as input tokens grow — even well inside the stated limit, every token added depletes a finite attention budget (Chroma "Context Rot" research, accessed 2026-06-02). Your job on a long task is to keep the live window lean and externalise everything else, so the work can run for hours across many fresh windows without losing the thread.
The one rule: if you can reconstruct a thing from a file or from git, it does not belong resident in the window. Keep load-bearing-right-now; evict the rest. The cost of forgetting is one re-read; the cost of hoarding is silent quality rot on every turn that follows.
Neighbours, so you don't do their job here: pricing tokens, spend ledgers and hard $ caps are ../cost-tracking/SKILL.md — same words ("token budget"), different unit, dollars vs. attention. Finding the right context via embeddings/chunking is ../rag/SKILL.md; RAG is how you find context, this is how much you let live and when to evict. Prompt text, few-shot and output format are ../prompt-engineering/SKILL.md; the agent loop, tool schemas and provider adapters are ../building-agents/SKILL.md; partition-then-gather fan-out of independent work is ../parallel/SKILL.md (this skill uses subagents as a context-isolation tactic but does not own that discipline); the 01-TOOLS / 02-DOCS control plane is ../harness/SKILL.md.
Read the gauge first
Before you do anything, estimate utilisation: live input tokens ÷ the model's window limit. You cannot manage a budget you are not watching.
- Compact early — around ~60% utilisation, not 80–95%. Most people only act when quality already broke at 80–95%; by then the rot already happened. Treat 60% as the line where you start reducing, not panicking (practitioner guidance on Claude Code
/compact, accessed 2026-06-02). - Trust the symptoms as an earlier trigger than the number. You can feel rot before the gauge confirms it:
- You re-read a file you already read this session.
- You restate the plan or a decision you already made.
- You contradict an earlier choice.
- Tool results from ten turns ago are still sitting verbatim in the window.
What ships with it
3 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.
- 8d ago First seen · 115 lines · 82 tokens per session scan A aaceab784492
context-budget is a skill published in the GitHub repository ericrisco/rsc-harness (70 stars, last pushed yesterday), licensed MIT. It adds 82 tokens to every session and 2,340 once invoked, about $0.0004 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
semantix
Install and use the semantix memory kernel as a middleware in your agent: extract user preferences / workflows / experience from past sessions, retrieve and inject them on demand. One binary + your agent's own tools.
self-improvement
Captures lessons and promotes recurring patterns.
evolve
Use this skill when extracting session patterns into reusable learnings. Three modes: analyze (extract from session history), review (edit/manage existing learnings), list (display active learnings). Manages .orchestrator/metrics/learnings.jsonl.
memory-cleanup
Use this skill when performing manual memory consolidation (Dream-equivalent). Reviews, consolidates, and prunes memory files under /.claude/projects//memory/. Run after major refactors, every 5+ sessions, or when memory quality degrades (broken links, stale references, contradictions, MEMORY.md > 200 lines). Invoke…
minimax-m3-long-context
How to use MiniMax M3's 1M-token MSA context productively: what to load vs. compress, when to retrieve vs. ingest, how to keep skills shallow in the always-on prompt and deep in skills, and how to plan retention across iterations. Load when the task might exceed 200K tokens, when the user asks to "keep all of this in…
session-handoff
Context transfer between AI sessions. Trigger when the user wants to save the context, resume a task, or hand off the work to another session.