Borrowing it
Nothing to install: this file belongs to kirill-markin/expense-budget-tracker. 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/kirill-markin/expense-budget-tracker/main/AGENTS.mdgit clone --depth 1 https://github.com/kirill-markin/expense-budget-trackerWrote 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/kirill-markin/expense-budget-tracker/agents-md)<a href="https://agentmods.dev/instructions/kirill-markin/expense-budget-tracker/agents-md"><img src="https://agentmods.dev/badge/instructions/kirill-markin/expense-budget-tracker/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/kirill-markin/expense-budget-tracker/agents-md"><img src="https://agentmods.dev/badge/instructions/kirill-markin/expense-budget-tracker/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 | $0.03101 | $0.03101 |
| Opus 5.5 | $0.01240 | $0.01240 |
| Sonnet 5.5 | $0.00620 | $0.00620 |
| Haiku 4.5 | $0.00310 | $0.00310 |
Grade A, and why
expense-budget-tracker 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 10d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
expense-budget-tracker
Open-source expense and budget tracker: expenses, budgets, balances, transfers, and multi-currency reporting on Postgres.
Rules
- Use English for code comments and documentation.
- Prefer functional programming and pure functions.
- Use classes only for connectors to external systems.
- Use strict typing across functions, variables, and collections.
- Avoid fallback logic unless explicitly requested.
- Raise explicit, actionable errors with context.
- Runtime discovery is the canonical machine API documentation. Keep its actions, instructions, and source links in sync with runtime behavior;
/v1/openapi.jsonand/v1/swagger.jsonare public source-discovery compatibility probes, not specification endpoints. - Version-bump requests must follow
docs/version-bump.mdand keepscripts/checks/pr/check-version-alignment.mjsgreen. - Never bump the version during ordinary work: a release publishes the version already in the repository, and a separate request bumps it right after each MCP Registry publication (
docs/mcp-registry-publishing.md). - Keep changes minimal and scoped to the current request.
- Before considering a large block of work complete, run the relevant type checks and builds, and for web changes a production build (
cd apps/web && npm run lint && npm run build). - Prefer non-interactive terminal commands.
- The web app supports multiple languages. When adding or changing any translation in
apps/web/src/i18n/, update the same keys in every locale file in that directory in the same change. - Change schema via new files in
db/migrations/only; never edit already-applied migrations. - CI/CD is GitHub Actions on push to
main(.github/workflows/deploy.yml), filtered by itspaths:list: a merge touching nothing in that list produces no Deploy run, which is correct and not a missed trigger. - The deploy process intentionally may update the web service before running migrations; this accepted deploy order is not an issue by itself.
- Do not build AWS SDK bundles or other AWS deployment artifacts locally. Push code to
main, and let CI/CD build and deploy everything. - Themeable colors belong in
apps/web/src/app/styles/tokens.cssunder both:rootand:root[data-theme="dark"]; write no new hex color anywhere else underapps/web/src, and keepscripts/checks/pr/check-css-hex-colors.mjsgreen. - RTL support is required:
- In CSS, use logical properties such as
inset-inline-start/end,margin-inline-start/end,padding-inline-start/end,border-inline-start/end, andtext-align: start/endinstead of physical left/right variants. - Use
[dir="rtl"]overrides only when no logical equivalent exists (for examplebox-shadow). - In JS, account for RTL when handling
scrollLeft, element positioning, and resize logic.
- In CSS, use logical properties such as
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.
- 10d ago Changed · +1 lines · +34 tokens per session 2dff7fa26bbc
- 23d ago Changed · +1 lines · +86 tokens per session 1cabb718f496
- 27d ago Changed · -1 lines · -31 tokens per session d41013005050
- 28d ago Changed · +1 lines · +69 tokens per session 700ec7b1d4bf
- 1mo ago Changed · +1 lines · +53 tokens per session 1e3515949804
- 1mo ago Changed · +3 lines · +105 tokens per session 5a4fc14ee6cb
- 1mo ago Changed · +99 tokens per session 6e81ec240cd8
- 1mo ago Changed · +4 lines · +253 tokens per session 4cfb1427ef1e
- 1mo ago Changed · +1 lines · +42 tokens per session cacb59556089
- 2mo ago First seen · 134 lines · 2,391 tokens per session scan A a122e2936d9c
expense-budget-tracker AGENTS.md is an instructions file published in the GitHub repository kirill-markin/expense-budget-tracker (41 stars, last pushed 3d ago), licensed MIT. It adds 3,101 tokens to every session, about $0.0124 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 2026-08-30.
expense-budget-tracker AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| expense-budget-tracker AGENTS.mdkirill-markin/expense-budget-tracker | Instructions file | 41 | 3d ago | MIT | A | 3,101 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | 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 | today | MIT | A | 4,680 | Codex, OpenCode |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 3,093 | GitHub Copilot |
| vscode model-prompts.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 2,022 | GitHub Copilot |