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 rules/lawofall/agentcore/seam-auditgit clone --depth 1 https://github.com/Lawofall/AgentCoreWhat 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 | $0.00075 | $0.00793 |
| Opus 5 | $0.00037 | $0.00396 |
| Sonnet 5 | $0.00015 | $0.00159 |
| Haiku 4.5 | $0.00007 | $0.00079 |
Grade A, and why
seam-audit 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.
What it actually says
接缝排查配方（interface-seam audit）
排查「一侧定义了、另一侧没接」的接缝 bug。逐轮结论正文见 git；公开仓不复述审计票号。
两类接缝签名（判据）
- 渲染画了却没接（drawn-but-not-wired）＝一侧有 UI/控件/动词/handler，却没把输出真正喂到另一侧、或输出被静默丢弃。
- 例：多选 scale 手柄画了不 hit-test；
board_ops的ref目标被 applier 丢。
- 例：多选 scale 手柄画了不 hit-test；
- 已铺管线·零产出（plumbed-but-zero-producer/consumer）＝字段/事件/路由/DB 列/类型在一侧已定义并承载，另一侧却无 producer（无人写/发）或无 consumer（无人读/渲）。
- 例：rotation 全链认却无 producer；
run_id后端发前端丢；辩论BatchMetrics收了不 emit。
- 例：rotation 全链认却无 producer；
铁律：判 gap 前先查文档（防误报）
判「有后端无前端 / 有前端无后端」为 gap 之前，先 grep docs/ 看是否记为有意休眠 / 退役 / ⏳待后端——大量「缺口」实为 by-design（质量档 UI 内测退役、admin LLM 窗待后端、mobile lite 减法）。
弱证据不冒充 bug，置信五档只对前两档动手：
GAP（真缺口·修）/ DRIFT（漂移·修）/ RESERVED（前瞻预留 → 远期规划）/ BY-DESIGN（有意 → 记档闭案）/ UNSURE（留观察）。
可复用配方
- 按面切分（画板/分享/admin/记忆/…）派并行只读探子，每子代理带「两签名 + 本铁律 + 五档置信 + 必附
file:line证据」（子代理模型见multitask.mdc）。与讨论并行时的主/子分相见multitask.mdc「讨论 + 审计分相」。 - 探子回报的 GAP 先 Read 源码复核——别信行号（复核曾翻过「有前端无后端」误报）；复核以外禁止主侧重跑整审计。
- 复核为实的 GAP·DRIFT 才修，改完
vitest/pytest+biome/ruff+tsc自检。 - RESERVED 进
远期规划、BY-DESIGN 记档闭案、UNSURE 留观察。
收口判据
每批稳定 ~2 真 bug、二批后边际递减（多为 by-design）即收口，别为凑数造 busywork。
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 · 34 lines · 75 tokens per session scan A c15c90c55fdb
seam-audit is a cursor rule published in the GitHub repository Lawofall/AgentCore (78 stars, last pushed 3d ago), licensed MIT. It adds 75 tokens to every session and 793 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 2026-08-30.
Other cursor rules, from other repositories
project-overview
Core project architecture, patterns, and conventions for the AI Documentation Generator.
code-patterns
Python code style and recurring patterns (config, logging, errors, paths).
core-project-context
Canonical project context and ownership rules.
backend-python
Python and FastAPI standards for the backend.
dashboard-typescript
React and TypeScript standards for the operator dashboard.
supabase-safety
Supabase migration, RLS and data security constraints.