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 daloopa/daloopa-plugin-claude --skill inflectiongit clone --depth 1 https://github.com/daloopa/daloopa-plugin-claudeWrote 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/daloopa/daloopa-plugin-claude/inflection)<a href="https://agentmods.dev/skills/daloopa/daloopa-plugin-claude/inflection"><img src="https://agentmods.dev/badge/skills/daloopa/daloopa-plugin-claude/inflection.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 | $0.00016 | $0.01462 |
| Opus 5 | $0.00008 | $0.00731 |
| Sonnet 5 | $0.00003 | $0.00292 |
| Haiku 4.5 | $0.00002 | $0.00146 |
Grade A, and why
inflection 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 7d 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
100% identical to inflection — 0 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Detect the biggest financial and operating inflections for the company specified by the user: $ARGUMENTS
Before starting, read ../data-access.md for data access methods and ../design-system.md for formatting conventions. Follow the data access detection logic and design system throughout this skill.
Follow these steps:
1. Company Lookup
Look up the company by ticker using discover_companies. Capture:
company_idlatest_calendar_quarter— anchor for all period calculations below (see../data-access.mdSection 1.5)latest_fiscal_quarter- Firm name for report attribution (default: "Daloopa") — see
../data-access.mdSection 4.5
2. Broad Series Discovery
Cast a wide net to discover ALL available series for this company. Search with multiple keyword sets to maximize coverage:
- Financial: "revenue", "income", "profit", "margin", "eps", "cash flow"
- Operating: "subscriber", "user", "customer", "unit", "arpu", "retention"
- Segment: "segment", "product", "service", "geographic"
- Balance sheet: "debt", "asset", "equity", "cash"
- Other: "backlog", "bookings", "pipeline", "store", "employee"
Collect all unique series IDs. The goal is comprehensiveness — capture every metric Daloopa tracks for this company.
3. Pull 8 Quarters of Data
Calculate 8 quarters backward from latest_calendar_quarter. Pull all discovered series for those periods. This gives enough history to compute both QoQ and YoY rates plus their second derivatives.
4. Compute Growth Rates and Inflections
For each series with sufficient data (at least 5 quarters):
YoY Growth Rate for each quarter:
- growth_t = (value_t - value_{t-4}) / |value_{t-4}|
YoY Acceleration (second derivative):
- accel_t = growth_t - growth_{t-1}
- Positive = accelerating, Negative = decelerating
QoQ Sequential Growth (for non-seasonal metrics):
- seq_growth_t = (value_t - value_{t-1}) / |value_{t-1}|
QoQ Acceleration:
- seq_accel_t = seq_growth_t - seq_growth_{t-1}
Skip series where values are too small (< 1% of revenue) or where data is sparse. For margin/ratio series (values between 0-1 or percentages), compute change in basis points rather than % change.
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.
- 7d ago First seen · 134 lines · 16 tokens per session scan A 1d4fb13d8407
inflection is a skill published in the GitHub repository daloopa/daloopa-plugin-claude (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 16 tokens to every session and 1,462 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to inflection, differing in 0 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.
strategy-pivot-designer
Detect backtest iteration stagnation and generate structurally different strategy pivot proposals when parameter tuning reaches a local optimum.
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
A framework for judging Chinese A-share stocks that have reached the daily price-rise limit, using market mood, sector leadership, and trading momentum.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
vectorbt
High-performance vectorized backtesting with parameter optimization, portfolio simulation, and rich performance metrics.