Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/heurist-network/heurist-financenpx agentmods add skills/heurist-network/heurist-finance/watchWrote 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/heurist-network/heurist-finance/watch)<a href="https://agentmods.dev/skills/heurist-network/heurist-finance/watch"><img src="https://agentmods.dev/badge/skills/heurist-network/heurist-finance/watch/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/heurist-network/heurist-finance/watch"><img src="https://agentmods.dev/badge/skills/heurist-network/heurist-finance/watch.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 | $0.00081 | $0.05546 |
| Opus 5 | $0.00041 | $0.02773 |
| Sonnet 5 | $0.00016 | $0.01109 |
| Haiku 4.5 | $0.00008 | $0.00555 |
Grade A, and why
watch 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 11d 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 — 611 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PREREQUISITE: Read
../../SKILL.md(two directories up from this file) first. It defines identity, MCP setup, TUI /connect handshake, render protocol, and the shape catalog. This file handles only the sub-skill-specific flow.
heurist-finance/watch - Heurist Finance Tracked Tickers Dashboard
What changed? Flag the movers.
This sub-skill is loaded by the main /heurist-finance router when the user
requests their Heurist Finance watchlist. MCP setup, tool tables, TUI detection, and render
dispatch protocol are already established by the parent SKILL.md - do not
repeat them here.
All MCP tools are prefixed mcp__heurist-finance__.
Watch Posture
Flag what's changed since last check, not just current state. The user doesn't need to see that AAPL is at $211 - they need to know it dropped 3% since yesterday on services revenue miss guidance.
For any mover >3%, state whether the move is noise or signal. A 3% drop on 10x average volume after an 8-K filing is signal. A 3% drop on normal volume in a sector-wide rotation is noise. Name it.
Session Memory
Before any MCP calls: read ~/.heurist/sessions/*.json. Filter by
tickers[] overlap with the current watchlist symbols. Sort by timestamp
descending, take last 5. For each ticker with a prior session, note the
conviction change inline ("AAPL was bearish last check, now neutral").
First run (no sessions dir): skip silently.
Interactive Flow
Ask in your own voice. The options below are guidance, not a script to read verbatim.
User Impatience Protocol
If the user says "skip" or their intent is clear (e.g., "just show me quick status for everything"): use sensible defaults and go. Don't force the interactive flow when intent is clear.
Step 1 - Load Watchlist
Read ~/.heurist/watchlist.json.
cat ~/.heurist/watchlist.json 2>/dev/null || echo '{"tickers":[]}'
Expected format:
{ "tickers": ["NVDA", "AAPL", "MSFT", "AMD", "TSLA"] }
If file is missing or tickers array is empty:
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.
- 11d ago First seen · 611 lines · 81 tokens per session scan A ad187d34c95f
watch is a skill published in the GitHub repository heurist-network/heurist-finance (10 stars, last pushed 5mo ago), licensed MIT. It adds 81 tokens to every session and 5,546 once invoked, about $0.0004 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
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.
furusato
A Japanese hometown-tax donation manager for furusato nozei, a system where donations to municipalities can qualify for an income-tax or local-tax deduction. It reads donation receipts, stores donation records, and calculates deduction limits.