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 skills add nota-america/forgecat-agent-profiles --skill comp-analysisgit clone --depth 1 https://github.com/nota-america/forgecat-agent-profilesWrote 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/nota-america/forgecat-agent-profiles/comp-analysis)<a href="https://agentmods.dev/skills/nota-america/forgecat-agent-profiles/comp-analysis"><img src="https://agentmods.dev/badge/skills/nota-america/forgecat-agent-profiles/comp-analysis.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 | $0.00051 | $0.00825 |
| Opus 5 | $0.00026 | $0.00413 |
| Sonnet 5 | $0.00010 | $0.00165 |
| Haiku 4.5 | $0.00005 | $0.00082 |
Grade A, and why
comp-analysis 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 4d 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.
This is a copy
94% identical to comp-analysis — 9 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/comp-analysis
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md (
.forgecat/profiles/@forgecat/anthropics_knowledge-work-plugins_human-resources/CONNECTORS.md).
Analyze compensation data for benchmarking, band placement, and planning. Helps benchmark compensation against market data for hiring, retention, and equity planning.
Usage
/comp-analysis $ARGUMENTS
What I Need From You
Option A: Single role analysis "What should we pay a Senior Software Engineer in SF?"
Option B: Upload comp data Upload a CSV or paste your comp bands. I'll analyze placement, identify outliers, and compare to market.
Option C: Equity modeling "Model a refresh grant of 10K shares over 4 years at a $50 stock price."
Compensation Framework
Components of Total Compensation
- Base salary: Cash compensation
- Equity: RSUs, stock options, or other equity
- Bonus: Annual target bonus, signing bonus
- Benefits: Health, retirement, perks (harder to quantify)
Key Variables
- Role: Function and specialization
- Level: IC levels, management levels
- Location: Geographic pay adjustments
- Company stage: Startup vs. growth vs. public
- Industry: Tech vs. finance vs. healthcare
Data Sources
- With ~~compensation data: Pull verified benchmarks
- Without: Use web research, public salary data, and user-provided context
- Always note data freshness and source limitations
Output
Provide percentile bands (25th, 50th, 75th, 90th) for base, equity, and total comp. Include location adjustments and company-stage context.
## Compensation Analysis: [Role/Scope]
### Market Benchmarks
| Percentile | Base | Equity | Total Comp |
|------------|------|--------|------------|
| 25th | $[X] | $[X] | $[X] |
| 50th | $[X] | $[X] | $[X] |
| 75th | $[X] | $[X] | $[X] |
| 90th | $[X] | $[X] | $[X] |
**Sources:** [Web research, compensation data tools, or user-provided data]
### Band Analysis (if data provided)
| Employee | Current Base | Band Min | Band Mid | Band Max | Position |
|----------|-------------|----------|----------|----------|----------|
| [Name] | $[X] | $[X] | $[X] | $[X] | [Below/At/Above] |
### Recommendations
- [Specific compensation recommendations]
- [Equity considerations]
- [Retention risks if applicable]
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.
- 4d ago First seen · 96 lines · 51 tokens per session scan A ce0c7c06532c
comp-analysis is a skill published in the GitHub repository nota-america/forgecat-agent-profiles (65 stars, last pushed today), licensed Apache-2.0. It adds 51 tokens to every session and 825 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to comp-analysis, differing in 9 lines, and is treated as a copy.
Other skills, from other repositories
sector-rotation
An analysis framework for comparing industries in the Chinese A-share stock market, using business conditions, price momentum, valuation, and money flows. It produces rankings and higher- or lower-allocation suggestions.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.
copy-trading
Skill "copy-trading" from Signal-Execution-Labs/forex-trading-ai-agent, covering copy trading, features, leader discovery, copy modes and risk management.
alipay-webhooks
Receive and verify Alipay (Antom / Alipay+) webhook notifications. Use when setting up Alipay webhook handlers, debugging RSA256 Signature header verification, or handling payment events like notifyPayment, notifyCapture, notifyRefund, notifyAuthorization, and notifyDispute.
lean-ma-cross-trend
A trend-analysis workflow using two moving averages, such as a fast and a slow line. A crossover occurs when one line moves above or below the other and is often used as a delayed sign of a possible trend change.
recipe-daily-pnl-report
Generate a daily profit and loss summary from trades and balances.