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 agentmods add skills/aaronsb/claude-code-config/context-statusnpx skills add aaronsb/claude-code-config --skill context-statusgit clone --depth 1 https://github.com/aaronsb/claude-code-configWhat 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 | $0.00048 | $0.00297 |
| Opus 5 | $0.00024 | $0.00148 |
| Sonnet 5 | $0.00010 | $0.00059 |
| Haiku 4.5 | $0.00005 | $0.00030 |
Grade A, and why
context-status 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.
What it actually says
Context Status
Run the context usage command and capture the JSON output:
ways context --json
Then render a visual gauge using the chart tool. Build the JSON and pipe it:
# Parse the values from the --json output, then:
echo '{"type":"hbar","data":{"Used (PCT%)":USED,"Free (RPCT%)":REMAINING},"title":"Context: USEDk / TOTALk tokens (MODEL)","width":60,"format":"human"}' \
| ~/.claude/hooks/ways/softwaredev/visualization/charts/chart-tool
Replace USED, REMAINING, TOTAL, PCT, RPCT, and MODEL with actual values from the JSON output. Use jq to extract them.
The command auto-detects the context window size from the model in the transcript (1M for Opus 4.6, 200k for others). Override with CLAUDE_CONTEXT_WINDOW env var.
If the remaining percentage is below 20%, mention that compaction is approaching and suggest wrapping up or prioritizing remaining work.
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 · 28 lines · 48 tokens per session scan A e4001f3cc68e
context-status is a skill published in the GitHub repository aaronsb/claude-code-config (18 stars, last pushed 5mo ago), licensed MIT. It adds 48 tokens to every session and 297 once invoked, about $0.0002 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
task-planning-arch
计算任务 gap 并产出下一步可执行子任务 List[TaskSpec];gap 已闭返回空数组。对齐 arch 场景(架构师名册/技术栈概览/双视角分析)确定式分解——按根目标交付物集合 + donechildren 查表(参照 task-planning storage 特例,非自由 LLM 分解)。.
task-search
在框架预查的候选 bot 集里决出执行者(who)与协作方式(how),返回 4 态 SearchResult(HITSINGLE/HITGROUP/HITMULTIBOTS/MISS)。对齐案例剧本确定式映射。.
task-planning
计算任务 gap 并产出下一步可执行子任务 List[TaskSpec];gap 已闭返回空数组。对齐案例剧本 gwqie46v7hzr1w6h(存储行业尽调)确定式分解。.
arch-analysis
输入(prompt / 子任务 instruction)中含关键词「某某某公司」即触发本 skill。触发后不联网、不做真实组织推断,直接返回下述 mock 伪造数据。.
agt-policy-authoring
Create and validate a minimal AGT Copilot CLI policy tailored to the repository being inspected.
silicon-throne
硅基圣座总控核心，以神谕式统御把零散任务压成 末将-first 之文明工程.