ljg-blind

ljg-blind is a skill for Claude Code from lijigang/ljg-skills. It costs 221 tokens per session (3,723 once invoked), scanned A, original, MIT.

A method for reviewing the previous day’s conversations with an AI to find one recurring way of thinking that hides relevant questions or evidence. It then chooses a book chapter intended to address that blind spot.

In plain words
What is it for?
Use it to scan conversations for patterns such as skipped issues, untested assumptions, repeated frameworks, or nearby questions left unasked, then create a focused analysis note based on a selected chapter.
Why use it?
It distinguishes a missing fact from a thinking habit that repeatedly prevents certain facts or viewpoints from being considered.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions subagents; mentions Codex.

Part of the ljg-skills plugin — 22 skills shipped together

Good fit Use it to scan conversations for patterns such as skipped issues, untested assumptions, repeated frameworks, or nearby questions left unasked, then create a focused analysis note based on a selected chapter.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lijigang/ljg-skills/ljg-blind
About the project

ljg-skills is a collection of custom Codex skills for tasks such as learning, writing, reading, relationship analysis, image creation, and investment analysis. Codex users install selected skills or the whole collection through a skills command-line interface. The catalogue entries are the collection's individual skills, plugin, and instruction.

lijigang/ljg-skills · 7,340 stars · on GitHub

Install

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.

Any agent
npx skills add lijigang/ljg-skills --skill ljg-blind
Clone the repo
git clone --depth 1 https://github.com/lijigang/ljg-skills

Made for: Claude Code.

Or install ljg-skills, the plugin that ships this one along with the rest of its 22 skills.

Wrote 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.

agentmods badge for ljg-blind

README.md
[![agentmods](https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-blind/github.svg)](https://agentmods.dev/skills/lijigang/ljg-skills/ljg-blind)
Your own site
<a href="https://agentmods.dev/skills/lijigang/ljg-skills/ljg-blind"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-blind/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ljg-blind

Your own site · 80×15
<a href="https://agentmods.dev/skills/lijigang/ljg-skills/ljg-blind"><img src="https://agentmods.dev/badge/skills/lijigang/ljg-skills/ljg-blind.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 221 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,723 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • Socket pass 17 Aug 2026
  • Snyk pass 17 Aug 2026
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Data Exfiltration · line 107
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Data Exfiltration · line 118
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00221 $0.03723
Opus 5 $0.00111 $0.01861
Sonnet 5 $0.00044 $0.00745
Haiku 4.5 $0.00022 $0.00372

Measured 12d ago against content hash a24aaf806c8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ljg-blind scanned grade A 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 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (Tools/WeReadWebUrl.ts), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s -X POST https://i.weread.qq.com/api/agent/gateway \
skills/ljg-blind/SKILL.md · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

盲区扫描

读你昨天跟 AI 的全部对话,照出那个你自己看不见的思维盲区,从微信读书点亮补它的一章。

盲区是什么

盲区不是知识缺口。不是"没读过某本书""不知道某个事实"——那种缺口,查一下就补上了。

盲区是一种结构性的思维习惯,它让某一类真相对你系统性地不可见。你不是想不到,是这个习惯让你压根没往那个方向看。它藏在你怎么想事情的方式里,不藏在你想的内容里。

所以证据不在"他说错了什么"。在——他没往哪看,他在哪绕了,他默认了什么却从没检。

五种盲区信号

从昨天的对话里找这五种。每一种都要落到具体的话上,不能凭感觉。

  1. 绕开点——一个难题他打开了,又飞快合上。证据:问题抛出,转头换话题,或一句"这个先不管"滑过去。
  2. 空转框架——反复换视角切同一个问题,没有一个落地。证据:一个问题被套上三四副框架,每副都浅尝辄止,最后没结论。
  3. 单一取景框——一整天只调用一两副 f(逢事就"约束""进化""博弈"),没试过别的镜子。这是他最隐蔽的盲区:越趁手的 f,越挡住别的 f 能照见的东西。(继刚看世界 = f(x),四轴是他默认的四副 f;正因为默认,才最该查他今天是不是又只用了其中一副。)
  4. 未检前提——一个默认假设贯穿全程,他当硬约束在用,从没问过它是不是假墙。证据:某个"本来就该这样"的说法,反复出现却从未被他自己质疑。
  5. 相邻空缺——从他问的东西反推,本该问、却没问的那个角落。不是凭空猜,是他自己的线索指向那儿。

选哪一个

从信号里挑 1 个作为今天的盲区。宁可一个说透,不要五个都点一遍——盲区的密度低于精度。判据三条:

  • 杠杆——补上它,下一步打开的可能性最多。
  • 真盲——是他自己看不见的,不是知道了在拖的。
  • 对位 mission——贴 M0(找新取景框)/ M1(求本质)。盲区若正好挡在他的主线上,优先。读 ${LIFEOS_DIR:-$HOME/.codex/LIFEOS}/USER/TELOS/PRINCIPAL_TELOS.md 确认主线。

操作步骤

第一步 · 定日期

# 默认昨天;用户传了 YYYY-MM-DD 就用那天(macOS BSD date)
target=${1:-$(date -v-1d +%Y-%m-%d)}

第二步 · 捞当天的对话

会话文件在 $HOME/.codex/sessions/YYYY/MM/DD/*.jsonl。目录日期按本机时间记录 session 的开始日,行内 timestamp 是 UTC;因此同时扫目标日与前一日目录,再按本机日期过滤消息。只读取顶层 task 的 response_item / message / user / input_text,排除 session_meta.payload.source.subagent 存在的子 agent 会话,以及 harness 包装和本次调用自身:

target=<上一步的日期>
out=/tmp/ljg-blind-${target}.txt
: > "$out"
previous_dir=$(date -j -v-1d -f '%Y-%m-%d' "$target" '+%Y/%m/%d')
target_dir=$(date -j -f '%Y-%m-%d' "$target" '+%Y/%m/%d')

for day_dir in "$previous_dir" "$target_dir"; do
  session_dir="$HOME/.codex/sessions/$day_dir"
  [ -d "$session_dir" ] || continue
  find "$session_dir" -type f -name '*.jsonl' -print0
done | while IFS= read -r -d '' session_file; do
  # Codex 将子 agent 与顶层 task 放在同一日期目录;从 session_meta 排除它们。
  if jq -e 'select(.type=="session_meta") |
      (.payload.source | type == "object" and has("subagent"))' \
      "$session_file" >/dev/null 2>&1; then
    continue
  fi

  jq -r --arg target "$target" '
    def local_epoch:
      sub("\\.[0-9]+Z$"; "Z") | fromdateiso8601;
    select(.type=="response_item"
      and .payload.type=="message"
      and .payload.role=="user")
    | (.timestamp | local_epoch) as $epoch
    | select(($epoch | strflocaltime("%Y-%m-%d")) == $target)
    | ([.payload.content[]?
        | select(.type=="input_text")
        | .text] | join("\n")) as $text
    | select($text | length > 0)
    | select(($text | test("^(<recommended_plugins>|<environment_context>|<task-notification>)")) | not)
    | select(($text | test("(?i)(ljg-blind|扫盲区)")) | not)
    | "[" + ($epoch | strflocaltime("%H:%M")) + "] " + $text
  ' "$session_file" 2>/dev/null >> "$out"
done

wc -m "$out"

Read the full file on GitHub · 215 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 12d ago First seen · 215 lines · 221 tokens per session scan A a24aaf806c8b

Subscribe to this mod's changes

ljg-blind is a skill published in the GitHub repository lijigang/ljg-skills (7,340 stars, last pushed 3d ago), licensed MIT. It adds 221 tokens to every session and 3,723 once invoked, about $0.0011 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…

garrytan/gbrain · 138 tokens

miniapp

Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.

yc-software/qm · 25 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

deck-course-module

A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.

nexu-io/html-anything · 25 tokens

master-yinguang

A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.

xr843/Master-skill · 274 tokens