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 ntaffzii/Skill-Agents --skill exposure-coachgit clone --depth 1 https://github.com/ntaffzii/Skill-AgentsWrote 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/ntaffzii/skill-agents/exposure-coach)<a href="https://agentmods.dev/skills/ntaffzii/skill-agents/exposure-coach"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/exposure-coach/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.
<a href="https://agentmods.dev/skills/ntaffzii/skill-agents/exposure-coach"><img src="https://agentmods.dev/badge/skills/ntaffzii/skill-agents/exposure-coach.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00138 | $0.00886 |
| Opus 5 | $0.00069 | $0.00443 |
| Sonnet 5 | $0.00028 | $0.00177 |
| Haiku 4.5 | $0.00014 | $0.00089 |
Grade A, and why
exposure-coach 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Exposure Coach
Overview
A daily market check produces several separate numbers (breadth %, uptrend %, account drawdown state) — this skill combines them into one plain-language read: how much new risk today's conditions support. It's the synthesis step at the end of a market-regime check, not a replacement for the individual skills that feed it.
Not financial advice. This is one configurable heuristic for summarizing market conditions plus your own account's risk state — not a signal to act on mechanically, and not a substitute for judgment about the specific setup in front of you.
When to use
- สรุปภาพรวมตลาดหลังเช็ค breadth และ uptrend แล้ว ว่าวันนี้ควร "เปิดรับความเสี่ยงใหม่" มากแค่ไหน
- Combining a market-regime read with the account's own drawdown state into one exposure-ceiling recommendation
- The synthesis step of a daily/weekly market check (after running market-breadth-analyzer and uptrend-analyzer)
When NOT to use
- Breadth/uptrend numbers haven't been computed yet — run those skills first; this skill has nothing to combine without them
- The user wants a signal for one specific stock — this is a market-wide/account-wide posture read, not a single-name call
Core knowledge
Priority rule: the account's own drawdown state always overrides a favorable market read. A "halt_new_positions" drawdown-gate state produces a "minimal" exposure ceiling regardless of how strong breadth/uptrend look — a personal risk rule isn't meant to be overridden by good market conditions. A "reduced_size" gate state caps the market-derived ceiling one notch lower.
Market-derived ceiling (before any drawdown adjustment):
| Breadth % | Uptrend % | Ceiling |
|---|---|---|
| ≥ 60% | ≥ 50% | High |
| ≥ 40% | ≥ 30% | Moderate |
| below both | — | Low |
These thresholds are a starting heuristic, not a validated model — like the individual skills feeding it, tune them against the user's own strategy history rather than treating them as fixed truth.
Common mistakes
What ships with it
1 file 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.
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.
- 9d ago First seen · 59 lines · 138 tokens per session scan A 0d52019a6bc4
exposure-coach is a skill published in the GitHub repository ntaffzii/Skill-Agents (4 stars, last pushed yesterday), licensed MIT. It adds 138 tokens to every session and 886 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
bionic-safety-net
Unified survival infrastructure: health, finance, legal safety, circuit breakers, and structural protection against all ruin classes. The last line of defense.
structural-trading-gate
Unified zero-emotion variance shield for capital markets (FX, crypto, CFDs) and poker. Absorbs trading-risk-gate + zenith-execution + trade-journal-analyzer into one engine.
zenith-execution
Unified trade execution suite: Half-Kelly sizing, stop-loss calculation, Monte Carlo simulation, and portfolio rebalancing. Absorbs: kelly-mandate, stop-loss-calc, monte-carlo-sim, portfolio-rebalancer.
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.
circuit-breaker
Mandatory systemic pause when cumulative red flags exceed threshold. Forces disengagement across Trading, Spending, Relationships, Work, and Energy domains.
tax-season-organizer
A Russian tax-period preparation workflow for small-business owners using simplified-tax or self-employed regimes. It collects figures and documents into a package for an accountant, rather than giving tax advice.