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/thinknpx skills add aaronsb/claude-code-config --skill thinkgit 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 | $0.00031 | $0.00518 |
| Opus 5 | $0.00015 | $0.00259 |
| Sonnet 5 | $0.00006 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
think 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 2d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Think Strategies
Explicit invocation of the structured thinking escalation. Use /think when you want to force an external reasoning strategy — the metacognitive check in the think way normally handles this autonomously.
Usage
/think # Show available strategies and select one
/think <strategy> # Invoke a specific strategy directly
Available Strategies
| Problem Shape | Skill | When to Use |
|---|---|---|
| Multiple viable approaches | /think-tree |
"What are the options?" — branch, evaluate, prune |
| Three competing objectives | /think-trilemma |
"We can't have all three" — satisfice |
| High-stakes decision | /think-consistency |
"Are we sure?" — independent paths, consensus |
| Stuck / need principles | /think-stepback |
"Why does this work?" — abstract, then apply |
| Investigation / debugging | /think-react |
"Figure out why" — reason-act-observe cycle |
When to Use /think Explicitly
- You want to force external reasoning even if the agent's metacognitive check would have stayed internal
- You want to choose a specific strategy rather than letting the agent select
- You want to see the reasoning — external strategies surface each step
The think way's escalation gradient (internal → external → collaborative) handles most cases automatically. /think is the manual override.
Session Lifecycle
Think sessions have a lifecycle: start → work stages → complete (or abandon).
Before starting a new session:
# Check for active think session
cat /tmp/.claude-think-session 2>/dev/null
- If a session is active, ask the user: finish it or abandon it first
- Do NOT start a new think session while one is active
Abandoning a session (user says "never mind", "skip it", changes topic):
rm -f /tmp/.claude-think-session /tmp/.claude-way-meta-think-*"${CLAUDE_SESSION_ID:+-$CLAUDE_SESSION_ID}" 2>/dev/null
After completion or abandonment, the think way can fire again for new problems.
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.
- 2d ago First seen · 57 lines · 31 tokens per session scan A eb5ee82c10e2
think is a skill published in the GitHub repository aaronsb/claude-code-config (18 stars, last pushed 4mo ago), licensed MIT. It adds 31 tokens to every session and 518 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
achieving-cmmc-level-2-compliance
Prepare a defense-contractor environment for CMMC Level 2 certification: scope CUI and FCI, implement the 110 NIST SP 800-171 Rev 2 security requirements across 14 families, compute the SPRS score with the DoD Assessment Methodology, manage a compliant POA&M, and ready the organization for a C3PAO assessment. Use when…
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。.
escalation-governance
Assess whether to escalate models. Use when evaluating reasoning depth.
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.