senior_analyst

senior_analyst is a skill for Claude Code, Codex from rrred0324/senior-analyst. It costs 92 tokens per session (10,897 once invoked), scanned C, original, MIT.

A business-analysis skill that checks whether a newer version is available and can guide an upgrade. The provided details do not fully describe its analysis work.

In plain words
What is it for?
Use it for the senior_analyst skill's version checks and upgrade process.
Why use it?
It can identify outdated installations and handle upgrade prompts or recovery when an upgrade fails.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the AskUserQuestion tool.

Not installable on its own: it runs a file from its repository that does not travel with it. Clone the repository, or install whatever ships that file. The line is python cli/track.py --list # 列出关注公司 + 最新快照.

Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

Made for: Claude Code, Codex.

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 senior_analyst

README.md
[![agentmods](https://agentmods.dev/badge/skills/rrred0324/senior-analyst/skill.svg)](https://agentmods.dev/skills/rrred0324/senior-analyst/skill)
Your own site
<a href="https://agentmods.dev/skills/rrred0324/senior-analyst/skill"><img src="https://agentmods.dev/badge/skills/rrred0324/senior-analyst/skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 10,897 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. Scan, not verified.
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 $0.00092 $0.10897
Opus 5 $0.00046 $0.05449
Sonnet 5 $0.00018 $0.02179
Haiku 4.5 $0.00009 $0.01090

Measured 6d ago against content hash a5d2ea48fa00, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade C, and why

senior_analyst scanned grade C 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 6d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$_BACKUP_DIR" "$_TEMP_DIR"
skill/SKILL.md · 810 lines

How it starts

The opening of the file, as written. The whole thing — 810 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Senior Analyst · 商业分析 Skill

版本检测(自动触发)

每次加载本 skill 时,执行以下命令自动检测版本:

_UC=""
# 优先从 ~/.local/bin 查找(install.sh / upgrade.sh 部署位置)
if [ -x "$HOME/.local/bin/senior_analyst-update-check" ]; then
    _UC=$("$HOME/.local/bin/senior_analyst-update-check" 2>/dev/null || true)
# 回退:从常见 repo clone 位置查找
elif [ -x "$HOME/ai-project/senior-analyst/bin/senior_analyst-update-check" ]; then
    _UC=$("$HOME/ai-project/senior-analyst/bin/senior_analyst-update-check" 2>/dev/null || true)
# 最终回退:跳过检测(未安装 update-check 脚本)
fi
[ -n "$_UC" ] && echo "$_UC" || true

输出的语义

  • UPGRADE_AVAILABLE <old> <new> → 按照下方 Inline 升级流程 处理
  • JUST_UPGRADED <old> <new> → 显示 "Running senior_analyst v{new} (just updated from v{old})!" 并继续当前任务
  • 空 → 继续当前任务

Inline 升级流程

当检测到 UPGRADE_AVAILABLE <old> <new> 时,按以下流程处理:

Step 1: 检查自动升级设置

_AUTO=$(cat ~/.config/senior_analyst/auto-upgrade 2>/dev/null || echo "false")
echo "AUTO_UPGRADE=$_AUTO"

如果 AUTO_UPGRADE=true: 跳过询问,直接执行 Step 2。如果升级失败,从备份目录恢复并通过 AskUserQuestion 告知用户:"Auto-upgrade failed — restored previous version v{old}. You can retry with /senior_analyst --upgrade."

否则: 通过 AskUserQuestion 提示用户:

senior_analyst 有新版本可用:v{old} → v{new}

选项:

  • A) Yes, upgrade now — 立即升级,完成后展示 What's New
  • B) Always keep me up to date — 启用自动升级,本次及以后都不再询问
  • C) Not now — 跳过本次提醒(snooze)
  • D) Never ask again — 永久关闭升级检测

如果选 A: 执行 Step 2。

如果选 B:

mkdir -p ~/.config/senior_analyst
echo "true" > ~/.config/senior_analyst/auto-upgrade

告知用户:"Auto-upgrade enabled. Future updates will install automatically." 然后执行 Step 2。

如果选 C: 写入 snooze 状态(递增延迟),然后继续当前 skill 任务,不再提及升级。

_SNOOZE_FILE="$HOME/.config/senior_analyst/update-snoozed"
_LEVEL=1
_NOW=$(date +%s)
if [ -f "$_SNOOZE_FILE" ]; then
    _SNOOZED_VER=$(awk '{print $1}' "$_SNOOZE_FILE")
    if [ "$_SNOOZED_VER" = "$_NEW_VER" ]; then
        _CUR_LEVEL=$(awk '{print $2}' "$_SNOOZE_FILE")
        case "$_CUR_LEVEL" in *[!0-9]*) _CUR_LEVEL=0 ;; esac
        _LEVEL=$((_CUR_LEVEL + 1))
    fi
fi
[ "$_LEVEL" -gt 3 ] && _LEVEL=3
echo "$_NEW_VER $_LEVEL $_NOW" > "$_SNOOZE_FILE"

告知用户延迟时长:"Next reminder in 24h"(或 48h / 1 week)。提示:"Set auto-upgrade: true via echo true > ~/.config/senior_analyst/auto-upgrade for automatic upgrades."

Read the full file on GitHub · 810 lines

Files

What ships with it

60 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. 6d ago First seen · 810 lines · 92 tokens per session scan C a5d2ea48fa00

Subscribe to this mod's changes

senior_analyst is a skill published in the GitHub repository rrred0324/senior-analyst (53 stars, last pushed 2mo ago), licensed MIT. It adds 92 tokens to every session and 10,897 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.