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 stevesolun/ctx --skill toolboxgit clone --depth 1 https://github.com/stevesolun/ctxWrote 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/stevesolun/ctx/toolbox)<a href="https://agentmods.dev/skills/stevesolun/ctx/toolbox"><img src="https://agentmods.dev/badge/skills/stevesolun/ctx/toolbox.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 | $0.00077 | $0.00674 |
| Opus 5 | $0.00039 | $0.00337 |
| Sonnet 5 | $0.00015 | $0.00135 |
| Haiku 4.5 | $0.00008 | $0.00067 |
Grade A, and why
toolbox 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 3d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
toolbox
Named bundles of skills/agents that run before (pre) or after (post)
a development task. Learn patterns from past work and propose new bundles.
Invoke slash, pre-commit, session-end, or file-save.
Quick reference
| Task | Command |
|---|---|
| Seed 5 starter toolboxes | python src/toolbox.py init |
| List available toolboxes | python src/toolbox.py list |
| Inspect one | python src/toolbox.py show ship-it |
| Activate (global) | python src/toolbox.py activate ship-it |
| Export for sharing | python src/toolbox.py export ship-it |
| Import a shared toolbox | python src/toolbox.py import file.yaml |
| Validate config | python src/toolbox.py validate |
Starter templates
| Name | When to use |
|---|---|
| ship-it | End-of-feature: 7-expert council on the change set |
| security-sweep | Security audit with guardrail blocking HIGH findings |
| refactor-safety | Refactors with graph-informed blast radius |
| docs-review | When touching Markdown or API docs |
| fresh-repo-init | Blank repo: run intent interview and scaffold |
Data model
Global: ~/.claude/toolboxes.json.
Per-repo (overrides global): <repo_root>/.toolbox.yaml.
Each toolbox declares:
pre— skills/agents to load before work startspost— agents that form the council after work endsscope.analysis—diff|full|graph-blast|dynamictrigger—slash,pre_commit,session_end, orfile_saveglobbudget.max_tokens/budget.max_seconds— hard stop on runaway costdedup.policy—fresh(always re-run) orcached(reuse within window)guardrail— if true, block commit on HIGH findings
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.
- 3d ago First seen · 63 lines · 77 tokens per session scan A a23b348c816e
toolbox is a skill published in the GitHub repository stevesolun/ctx (583 stars, last pushed 7d ago), licensed MIT. It adds 77 tokens to every session and 674 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 2026-09-03.
Other skills, from other repositories
skill-factory
A workflow that examines completed session work and turns reusable patterns into Claude Code skills.
session-wrap
Use when wrapping up a session before ending. 4 parallel subagents detect doc updates, repeated patterns, learning points, and follow-ups, then a verifier deduplicates and presents choices. Triggers on /session-wrap, session wrap, session cleanup, end of session.
relay
Session relay — compresses what's been done so far (writes a one-liner for /compact) and generates a "next task" prompt (a baton) for the user to hand off. Use on requests like "relay / hand off / next session / continue after compact / baton / handoff / clean up context and continue next task." Does not run /compact…
strategic-compact
Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.
customer-success
Support workflows, ticketing systems (Zendesk, Intercom), knowledge base design, chatbot design, and metrics (CSAT, NPS). Use when building support infrastructure, designing help centers, or optimizing customer experience.
event-planner
Event planning with timelines, budgets, vendor coordination, logistics checklists, and post-event evaluation. Use when organizing conferences, workshops, galas, or corporate events.