agentmods.dev

heurist-finance: Skill for Claude Code

.claude/skills/entry-exit-timing/SKILL.md

entry-exit-timing is a skill for Claude Code from heurist-network/heurist-finance. It costs 105 tokens per session (1,991 once invoked), scanned A, original, MIT.

A guide to choosing entry and exit prices for an existing investment or trading idea. It classifies whether prices are trending or moving within a range, then uses measured price levels to plan orders, stops, and targets.

In plain words
What is it for?
Use it to plan limit-order ladders, assess trend and range conditions, describe momentum with MACD, map pullback zones with Fibonacci levels, and set stop-loss and profit targets.
Why use it?
Timing tools cannot create a sound investment reason, and the same tactic can fail in a trend or a range. Starting with the market regime helps avoid applying a pullback or breakout method in the wrong conditions.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is heurist-network/heurist-finance's own configuration. It tells Claude Code how to work on heurist-finance itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything heurist-finance configures →

not rated 11repo 14d ago A scan 105 tokens original MIT
View source ↗ heurist-network/heurist-finance finance.heurist.ai
Reuse

Borrowing it

Nothing to install: this file belongs to heurist-network/heurist-finance. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/heurist-network/heurist-finance/main/.claude/skills/entry-exit-timing/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/heurist-network/heurist-finance

Made for: Claude Code.

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 entry-exit-timing

README.md
[![agentmods](https://agentmods.dev/badge/skills/heurist-network/heurist-finance/entry-exit-timing/github.svg)](https://agentmods.dev/skills/heurist-network/heurist-finance/entry-exit-timing)
Your own site
<a href="https://agentmods.dev/skills/heurist-network/heurist-finance/entry-exit-timing"><img src="https://agentmods.dev/badge/skills/heurist-network/heurist-finance/entry-exit-timing/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.

agentmods 80×15 button for entry-exit-timing

Your own site · 80×15
<a href="https://agentmods.dev/skills/heurist-network/heurist-finance/entry-exit-timing"><img src="https://agentmods.dev/badge/skills/heurist-network/heurist-finance/entry-exit-timing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,991 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00105 $0.01991
Opus 5.5 $0.00042 $0.00796
Sonnet 5.5 $0.00021 $0.00398
Haiku 4.5 $0.00011 $0.00199

Measured 13d ago against content hash a36217706765, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

entry-exit-timing 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 13d 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.

.claude/skills/entry-exit-timing/SKILL.md · 49 lines

How it starts

The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Entry & Exit Timing

Shared plumbing and output contract: ../_shared/analyst-core.md. Scope discipline first: timing sits on top of a thesis, it doesn't create one. This skill takes a direction that already exists on other grounds (any style skill) and answers when and at what price — its value is improving the entry/exit price distribution and forcing pre-committed levels, worth real basis points but never a substitute for edge. If no thesis exists, route to a style skill first.

Step 1 — Classify the regime (this decides everything)

The universal timing error is applying a mean-reversion tool in a trend or a breakout tool in a range. Classify before choosing, from prices SYM --period 1y --out FILE + technical_snapshot, computed not eyeballed:

  • Efficiency ratio (Kaufman): |net change over 20d| ÷ sum of |daily changes|. > ~0.4 = trending; < ~0.2 = ranging; between = mixed (halve size or stand aside).
  • Corroborate: price vs 50/200d structure and slope; Bollinger band width percentile (squeezes precede expansion — a 6-month-low band width says the next move is a break, not a fade); MACD histogram sign and slope as the trend descriptor it honestly is (Tier 2 per technical-evidence — a smoothed trend state, not an entry oracle; its crosses lag ~by construction and whipsaw in ranges).
  • The mapping: trending → buy pullbacks / breakout retests in trend direction only; never fade band touches against the trend (riding the upper band is what strong trends do — "overbought" is a trend's natural state). Ranging → fade the extremes toward the mean, both directions eligible. This split is the entire reason band fades sometimes "work great" and sometimes bleed — the tool didn't change, the regime did.
  • When daily and weekly disagree, the thesis horizon governs: a multi-week thesis trades the weekly regime and uses the daily read only for entry location; if the setup exists only on the daily, it's a shorter trade than the thesis — say so and treat it as one.
  • Before recommending any fresh entry, establish the current market-health gate (run its quick dashboard — index trend + distribution count — if not already known this session) and name it in the Call; a REDUCE_ONLY tape caps fresh-entry recommendations.

Read the full file on GitHub · 49 lines

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. 13d ago First seen · 49 lines · 105 tokens per session scan A a36217706765

Subscribe to this mod's changes

entry-exit-timing is a skill published in the GitHub repository heurist-network/heurist-finance (11 stars, last pushed 14d ago), licensed MIT. It adds 105 tokens to every session and 1,991 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-24.

Finance and fintechai-agentscodex
Related

entry-exit-timing compared with skills from other repositories

entry-exit-timing next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
entry-exit-timingheurist-network/heurist-financeSkill1114d agoMITA105Claude Code
sector-rotationHKUDS/Vibe-TradingSkill38kyesterdayMITA39Claude Code, Codex
twitter-readerhimself65/finance-skillsSkill3.5k2d agoMITA110Claude Code
strategy-pivot-designertradermonty/claude-trading-skillsSkill3.7k2d agoMITA28Claude Code, Codex
energy-procurementhashgraph-online/awesome-codex-pluginsSkill1.5kyesterdayApache-2.0A93Claude Code, Codex
airdrop-hunting-guidenirholas/three.wsSkill269yesterdayApache-2.0A54Claude Code, Codex
multi-expert-analyzerdigoal/blogSkill8.6k2d agoGPL-2.0A292Codex