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/think-stepbacknpx skills add aaronsb/claude-code-config --skill think-stepbackgit clone --depth 1 https://github.com/aaronsb/claude-code-configWrote 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/aaronsb/claude-code-config/think-stepback)<a href="https://agentmods.dev/skills/aaronsb/claude-code-config/think-stepback"><img src="https://agentmods.dev/badge/skills/aaronsb/claude-code-config/think-stepback.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 | $0.00036 | $0.00272 |
| Opus 5 | $0.00018 | $0.00136 |
| Sonnet 5 | $0.00007 | $0.00054 |
| Haiku 4.5 | $0.00004 | $0.00027 |
Grade B, and why
think-stepback scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/hooks/ways/meta/think/strategies/step-back.md What it actually says
Step-Back
Start Session
Before beginning, register this think session:
# Check for active session
if [[ -f /tmp/.claude-think-session ]]; then cat /tmp/.claude-think-session; fi
If another session is active, ask the user to finish or abandon it first. Otherwise:
echo "step-back" > /tmp/.claude-think-session
Work Through Stages
Read the strategy definition and follow its stages in order:
cat ~/.claude/hooks/ways/meta/think/strategies/step-back.md
Work through each numbered stage sequentially. Do not skip stages. Present your work for each stage before moving to the next.
Complete Session
After the final stage, clean up so the think way can fire again:
rm -f /tmp/.claude-think-session /tmp/.claude-way-meta-think-*"${CLAUDE_SESSION_ID:+-$CLAUDE_SESSION_ID}" 2>/dev/null
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.
- 4d ago First seen · 41 lines · 36 tokens per session scan B 2a1213886087
think-stepback is a skill published in the GitHub repository aaronsb/claude-code-config (18 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 272 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.