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.
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.
[](https://agentmods.dev/skills/rrred0324/senior-analyst/skill)<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>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 5.1 | $0.00092 | $0.10897 |
| Opus 5 | $0.00046 | $0.05449 |
| Sonnet 5 | $0.00018 | $0.02179 |
| Haiku 4.5 | $0.00009 | $0.01090 |
Grade C, and why
senior_analyst scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$_BACKUP_DIR" "$_TEMP_DIR" How it starts
The opening of the file, as written. The whole thing — 810 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Senior Analyst · 商业分析 Skill
版本检测(自动触发)
每次加载本 skill 时,执行以下命令自动检测版本:
_UC=""
# 优先从 ~/.local/bin 查找(install.sh / upgrade.sh 部署位置)
if [ -x "$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."
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.
- council.md 9.1 KB
- data_protocol.md 17 KB
- evidence_levels.md 5.0 KB
- examples/case_competitive_benchmark.md 1.3 KB
- examples/case_finance_redflag.md 633 B
- examples/case_metric_drop.md 951 B
- examples/case_pmf_judgment.md 905 B
- examples/case_strategy_choice.md 945 B
- export_protocol.md 1.1 KB
- glossary.md 7.1 KB
- knowledge/business_modeling_overview.md 6.4 KB
- knowledge/industries_lite/ai_lite.md 1.4 KB
- knowledge/industries_lite/automotive_lite.md 1.4 KB
- knowledge/industries_lite/beauty_lite.md 1.2 KB
- knowledge/industries_lite/consumer_electronics_lite.md 1.3 KB
- knowledge/industries_lite/consumer_lite.md 1.1 KB
- knowledge/industries_lite/ecommerce_lite.md 1.1 KB
- knowledge/industries_lite/education_lite.md 1.2 KB
- knowledge/industries_lite/enterprise_service_lite.md 1.2 KB
- knowledge/industries_lite/entertainment_lite.md 1.2 KB
- knowledge/industries_lite/finance_lite.md 1.4 KB
- knowledge/industries_lite/fintech_lite.md 1.3 KB
- knowledge/industries_lite/gaming_lite.md 1.3 KB
- knowledge/industries_lite/going_global_lite.md 1.3 KB
- knowledge/industries_lite/healthcare_lite.md 1.3 KB
- knowledge/industries_lite/home_furniture_lite.md 1.2 KB
- knowledge/industries_lite/industrial_automation_lite.md 1.2 KB
- knowledge/industries_lite/local_life_lite.md 1.3 KB
- knowledge/industries_lite/logistics_supply_chain_lite.md 1.2 KB
- knowledge/industries_lite/maternity_baby_lite.md 1.2 KB
- knowledge/industries_lite/media_advertising_lite.md 1.3 KB
- knowledge/industries_lite/new_energy_lite.md 1.3 KB
- knowledge/industries_lite/pet_lite.md 1.2 KB
- knowledge/industries_lite/real_estate_lite.md 1.1 KB
- knowledge/industries_lite/restaurant_lite.md 1.3 KB
- knowledge/industries_lite/saas_lite.md 1.1 KB
- knowledge/industries_lite/semiconductor_lite.md 1.3 KB
- knowledge/industries_lite/travel_lite.md 1.3 KB
- knowledge/industries_lite/web3_lite.md 1.4 KB
- knowledge/industries/ai.md 9.1 KB
- knowledge/industries/automotive.md 14 KB
- knowledge/industries/beauty.md 10 KB
- knowledge/industries/consumer_electronics.md 12 KB
- knowledge/industries/consumer.md 11 KB
- knowledge/industries/ecommerce.md 8.4 KB
- knowledge/industries/education.md 11 KB
- knowledge/industries/enterprise_service.md 12 KB
- knowledge/industries/entertainment.md 11 KB
- knowledge/industries/finance.md 12 KB
- knowledge/industries/fintech.md 12 KB
- knowledge/industries/gaming.md 10 KB
- knowledge/industries/going_global.md 11 KB
- knowledge/industries/healthcare.md 9.8 KB
- knowledge/industries/home_furniture.md 9.8 KB
- knowledge/industries/industrial_automation.md 11 KB
- knowledge/industries/local_life.md 12 KB
- knowledge/industries/logistics_supply_chain.md 9.7 KB
- knowledge/industries/maternity_baby.md 12 KB
- knowledge/industries/media_advertising.md 9.2 KB
- knowledge/industries/new_energy.md 9.5 KB
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.
- 6d ago First seen · 810 lines · 92 tokens per session scan C a5d2ea48fa00
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.
Other skills, from other repositories
finance-skills
Financial analyst agent skill and plugin for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw. Ratio analysis, DCF valuation, budget variance, rolling forecasts. 4 Python tools (stdlib-only).
financial-analysis
Build institutional-grade financial analyses: comparable company analysis, DCF valuation, LBO model, and Excel spreadsheet workflows. Functions: Comps Analysis: Build comparable company analyses with valuation multiples DCF Model: Discounted Cash Flow valuation models LBO Model: Leveraged Buyout modeling 3-Statements…
equity-deep-dive
A thorough single-equity deep dive — read the recent qualitative picture from the web, then ground it in fundamentals and health ratios, an intrinsic DCF with a sensitivity range, a comparable-company cross-check, and the analyst-consensus view.
stock-valuation
Multi-method stock valuation using DCF, comparable company analysis, EV multiples, and residual income models.
technical-analysis
Technical analysis of US stocks using charts and indicators.
competitor-analysis
Deep competitive moat analysis, market position assessment, and industry dynamics.