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 cveralyon/axel-setup --skill context-budgetgit clone --depth 1 https://github.com/cveralyon/axel-setupWrote 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/cveralyon/axel-setup/context-budget)<a href="https://agentmods.dev/skills/cveralyon/axel-setup/context-budget"><img src="https://agentmods.dev/badge/skills/cveralyon/axel-setup/context-budget.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.01120 |
| Opus 5 | $0.00028 | $0.00560 |
| Sonnet 5 | $0.00011 | $0.00224 |
| Haiku 4.5 | $0.00006 | $0.00112 |
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 7d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Budget
Estimate the token overhead of everything loaded into a Claude Code session and surface concrete ways to reclaim context space. Adapted from ECC's context-budget for a single-runtime (Claude Code) setup on a large Opus window.
When to Use
- The setup has grown (many agents, hooks, skills, MCP servers) and you want the real load cost.
- Output quality degrades, or the context monitor fires earlier than expected.
- Before adding more agents, skills, or MCP servers: check headroom first.
- Running the
/context-budgetcommand (this skill backs it).
How It Works
Token estimation: prose uses words × 1.3, code or JSON uses chars / 4.
Phase 1 — Inventory
Scan each source and estimate tokens.
- Agents (
~/.claude/agents/*.md): tokens per file. Flag files over 200 lines (heavy) and adescriptionover 30 words (it loads into every Task tool invocation, even for agents never spawned). - Skills (
~/.claude/skills/*/SKILL.md): tokens per SKILL.md. Flag over 400 lines. - Commands (
~/.claude/commands/*.md): tokens per file. Flag stale or duplicated entries. - Hooks (
~/.claude/hooks/plus the wiring insettings.json): count active hooks. Flag heavy or overlapping ones. - MCP servers (active MCP config): count servers and total tools. Estimate ~500 tokens per tool schema. Flag servers over 20 tools, and servers that wrap a CLI already available for free (gh, git, vercel, supabase).
- CLAUDE.md and memory chain (
~/CLAUDE.md,~/.claude/memory/MEMORY.md, any project CLAUDE.md): tokens per file. Flag a combined total over 400 lines, or a MEMORY index that carries detail instead of one-line pointers.
Note on RTK: it compresses Bash OUTPUT at runtime. It does not reduce the LOAD cost of this setup. Measure the load cost (the files above), not RTK-filtered command output.
Phase 2 — Classify
| Bucket | Criteria | Action |
|---|---|---|
| Always needed | Referenced in CLAUDE.md, backs an active command, or matches current work | Keep |
| Sometimes needed | Domain-specific, not referenced in CLAUDE.md | On-demand or lazy-load |
| Rarely needed | No reference, overlapping content, no project match | Remove or archive |
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.
- 7d ago First seen · 87 lines · 55 tokens per session scan A 991fee71e40a
context-budget is a skill published in the GitHub repository cveralyon/axel-setup (4 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 1,120 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
taiyi-compress
A workflow tool for shrinking large coding-agent conversations and work files into shorter context notes. It can also coordinate separate agents for parallel development and create handoff notes for continuing work in a new session.
continuous-learning-v2
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents.
codebase-memory-mcp
Resolve canonical Git checkouts, index and verify codebase-memory-mcp graphs through the guarded CLI, and safely audit duplicate worktree caches. Use when a user mentions codebase memory MCP, searchgraph, tracepath, indexrepository, worktree indexes, or oversized graph caches.
project-memory
Initialize, retrieve, and explicitly update the separate Rootloom Memory plugin's repository-owned architecture, risk, decision, and failure lessons. Use only when explicitly requested. Memory is experimental, advisory, and outside Rootloom Core.
memory-hygiene
Keep agent-written memory files from rotting. Audits /.claude/projects/ /memory/ for facts the tree now contradicts — stale version pins, passed sequence facts, vanished paths — plus MEMORY.md index drift, and enforces the memory format contract at write time. Use when the user says "audit my memory", "memory is…
learn-on-failure
Save a learning to project memory. Invoke automatically (without the user asking) whenever a task required more than one fix cycle to resolve — e.g. a test failed and needed a second attempt, a compile error required a correction, an API behaved unexpectedly, or an assumption proved wrong mid-task. Also invoke when…