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 commands/bigkunlun/ai-coding-insights/resetgit clone --depth 1 https://github.com/BigKunLun/AI-Coding-InsightsWrote 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/commands/bigkunlun/ai-coding-insights/reset)<a href="https://agentmods.dev/commands/bigkunlun/ai-coding-insights/reset"><img src="https://agentmods.dev/badge/commands/bigkunlun/ai-coding-insights/reset.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 | $0.00068 | $0.00699 |
| Opus 5 | $0.00034 | $0.00349 |
| Sonnet 5 | $0.00014 | $0.00140 |
| Haiku 4.5 | $0.00007 | $0.00070 |
Grade A, and why
reset 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
你要帮用户清掉本机可再生的评估产物，好让 scan 不被 30 天增量窗口闸门（too_soon）挡下，能干净重跑。
删除动作的本体在规则层 reset 子命令（合「删除收在规则层」约定），你不要自己跑 rm。承重边界已写死在纯函数 reset_targets 里：只清 ~/.ai-coding-insights/ 下的 4 个产物（snapshots/ reports/ run/ auto-scan.log），~/.claude/ai-coding-insights/config.toml 与会话原文永不在目标集。
另一关键动作：reset 会把今日写进 .auto-scan.lock（而非删它）——SessionEnd 的后台 auto-scan 见今日锁即整天跳过，不会抢先写新快照把 30 天闸门重新武装。这正是「reset 后重跑仍 too_soon」的根因修复：删锁会解除抑制、让 auto-scan 抢占刚清空的游标。
按顺序执行：
- 先预览——跑 dry-run 列出将删清单，原样展示给用户：
!uv run --project ${CLAUDE_PLUGIN_ROOT} python -m ai_coding_insights reset --dry-run
-
要确认（硬闸，不可跳过）——把上面的清单复述给用户，明确这是不可逆删除（虽都可再生），用
AskUserQuestion问「确认清掉这些产物吗？」。即使用户的首条消息已说「reset 后重跑」，也必须先展示清单、拿到这一轮的明确「是」，再进第 3 步——绝不在同一回合内未确认就真删。 用户说「否/取消」则到此为止。 -
再真删——用户点头后，去掉
--dry-run跑一次，把规则层打印的「已删 + 已置锁」清单回给用户，并告知：下次scan会以first状态重新取数，且当天的后台 auto-scan 已被锁压住、不会再抢占：
uv run --project ${CLAUDE_PLUGIN_ROOT} python -m ai_coding_insights reset
若预览阶段显示「无产物可删」，说明产物本已干净——但仍建议执行真删以置今日锁、压住 auto-scan 抢占（除非用户只是想看看）。
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 · 68 tokens per session scan A 6092a76d9546
reset is a command published in the GitHub repository BigKunLun/AI-Coding-Insights (5 stars, last pushed 15d ago), licensed MIT. It adds 68 tokens to every session and 699 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.