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.
curl -O https://raw.githubusercontent.com/heurist-network/heurist-finance/main/AGENTS.mdgit clone --depth 1 https://github.com/heurist-network/heurist-financeWrote 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/instructions/heurist-network/heurist-finance/agents-md)<a href="https://agentmods.dev/instructions/heurist-network/heurist-finance/agents-md"><img src="https://agentmods.dev/badge/instructions/heurist-network/heurist-finance/agents-md/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/instructions/heurist-network/heurist-finance/agents-md"><img src="https://agentmods.dev/badge/instructions/heurist-network/heurist-finance/agents-md.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 | $0.03235 | $0.03235 |
| Opus 5.5 | $0.01294 | $0.01294 |
| Sonnet 5.5 | $0.00647 | $0.00647 |
| Haiku 4.5 | $0.00324 | $0.00324 |
Grade A, and why
heurist-finance AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Heurist Finance
A workspace for investment research, trading plans and price monitoring. Any AI agent (Claude Code, Codex, Cursor, phone agents) can work here; the git repo is the source of truth for plans, positions, trades and research notes.
Read profile.md first: who the user is, their stance, what never to pitch, and lessons from past trades. If it is still the template, offer to interview the user and fill it in.
Layout
profile.md: the user. Update when they tell you something new; Lessons are appended only bytrade-postmortem.trading/plans/YYYY-MM-DD-<slug>.md: one trading plan per file (frontmatter below + the 8 sections from thetrading-planskill). A closed plan keeps its file withstatuschanged and a## Postmortemsection.0000-00-00-example.mdshows the shape.trading/portfolio.md: current holdings and cash.trading/trades.md: one row per fill. Every row names the plan level it executed (plan+levelid) orunplanned. Receipt screenshots go totrading/receipts/.trading/watches/<slug>.md: conditions that need judgement rather than a price level (see Watches).research/: notes, one topic per file, source URLs included.messages/YYYYMMDD-N-<topic>.md: the daily briefs (quick reads, not deep research; follow up inresearch/when a topic deserves it).context/latest.md: the working notes of the two most recent brief runs, newest first, each headed with its date and time: snapshot of every holding and plan ticker, macro readings, all stories found (sent or not, with dates and URLs), the 10-day calendar, open threads. Older runs live in git history.context/index.md: per ticker, recent facts a model cannot know from training: high-confidence, high-value, dated, with a URL. Kept 30 days, at most 10 per ticker..claude/skills/: analysis skills (trading-plan,hf-research,earnings-preview,entry-exit-timing,position-sizing,trade-postmortem, …)..agents/skillslinks here for non-Claude agents. Shared rules:.claude/skills/_shared/analyst-core.md.scripts/hf_tool.py: market data CLI.scripts/monitor.py: level/event monitor.scripts/watch.py: judgement watches.scripts/brief.py: daily brief agent.src/is their support code.
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.
- 13d ago Changed · -58 lines · +897 tokens per session 8319a5a38717
- 2mo ago First seen · 189 lines · 2,338 tokens per session scan A 79ceca822dfd
heurist-finance AGENTS.md is an instructions file published in the GitHub repository heurist-network/heurist-finance (11 stars, last pushed 14d ago), licensed MIT. It adds 3,235 tokens to every session, about $0.0129 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 2026-08-31.
heurist-finance AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| heurist-finance AGENTS.mdheurist-network/heurist-finance | Instructions file | 11 | 14d ago | MIT | A | 3,235 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |