Borrowing it
Nothing to install: this file belongs to the-mace/loseit-mcp-local. 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/the-mace/loseit-mcp-local/main/AGENTS.mdgit clone --depth 1 https://github.com/the-mace/loseit-mcp-localWrote 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/the-mace/loseit-mcp-local/agents-md)<a href="https://agentmods.dev/instructions/the-mace/loseit-mcp-local/agents-md"><img src="https://agentmods.dev/badge/instructions/the-mace/loseit-mcp-local/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/the-mace/loseit-mcp-local/agents-md"><img src="https://agentmods.dev/badge/instructions/the-mace/loseit-mcp-local/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 | $0.01253 | $0.01253 |
| Opus 5.5 | $0.00501 | $0.00501 |
| Sonnet 5.5 | $0.00251 | $0.00251 |
| Haiku 4.5 | $0.00125 | $0.00125 |
Grade A, and why
loseit-mcp-local 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 4d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LoseIt Local MCP: agent instructions
Shared rules (pull before work, tests and lint, secrets, commit attribution)
live in the global ~/.config/agents/AGENTS.md. If that file is not loaded
(cloud or CI sessions), the short version is: git pull --ff-only first, run
the tests below before committing, never commit secrets, and end agent commits
with a Co-Authored-By: <Tool> (<model>) <email> trailer.
Which coding agent
Use Claude Code with Sonnet for small, contained fixes driven by an alert email (scrape timeouts, expired sessions, catch-up runs). Use Opus 5.5 for multi-file, schema, or session-security changes. Grok Build is the second opinion.
Repo specifics
- After a pull that touches
requirements.txt:source .venv/bin/activate && pip install -r requirements.txt, and if Playwright changed,python -m playwright install chromium. - Tests:
.venv/bin/python -m pytest(CI runs the same suite).
Context
I use LoseIt (loseit.com) for diet/calorie tracking. There's no official
API and no working data export on the web app. This project scrapes my
own account via a headless browser, stores it locally, and exposes it to
Claude Desktop via MCP — mirroring an existing Garmin MCP setup I already
have running (same architecture: local Playwright/Python scraper → SQLite
→ stdio MCP server → claude_desktop_config.json).
Known constraint: this scrapes a personal account via the web UI and will be fragile against LoseIt UI changes. Flag clearly if something during the build makes unattended daily runs non-viable (e.g. LoseIt requires solving a CAPTCHA on every login).
Layout
src/db.py— SQLite schema + helpers (daily_summary,food_log,weight_log,water_log).src/loseit_mcp.py— MCP server (mcp v2) exposing 4 read-only tools:get_daily_summary,get_food_log,get_weight_history,get_water_log.src/auth.py— login and token refresh through the iOS app's OAuth endpoint (sync.loseit.com/account/login, found by capturing the app's traffic). Tokens in~/.loseit-data/tokens.json; the access token doubles as the webfn_auth/liauthcookies.src/scraper.py— Playwright scraper.loginprompts for email/password and logs in viaauth.py(--browserfor the old headed-browser login);runrefreshes the token, then fetches yesterday (or--since YYYY-MM-DD),--headedfor a visible browser.fetch_day,fetch_weight, andfetch_waterread the live site. Individual exercise entries are deliberately not scraped; only the day's exercise-calorie total is kept, so remaining calories match LoseIt's own figure.src/daily_email.py— renders one stored day as the bot-parsableloseit-daily/1email body;run-scraper.shsends it toLOSEIT_DAILY_SUMMARY_EMAILafter a successful run. Changing the format breaks downstream parsers: bump theformat:version.scripts/install-launchd.sh— writes launchd agents into~/Library/LaunchAgentswith absolute paths derived at install time (labels:com.loseit-mcp.scraper,com.loseit-mcp.scraper-health).--email/--summary-emailput the addresses in the plist env only; never commit a real address.requirements.txt— playwright, mcp, httpx (token API).
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.
- 4d ago Changed · +6 lines · +102 tokens per session b06edf1619a2
- 20d ago Changed · +6 lines · +113 tokens per session 01a67b4fdea5
- 1mo ago Changed · +63 lines · +898 tokens per session 6aeb78fb8019
- 2mo ago First seen · 24 lines · 140 tokens per session scan A db1b45d510f6
loseit-mcp-local AGENTS.md is an instructions file published in the GitHub repository the-mace/loseit-mcp-local (0 stars, last pushed 2d ago), licensed MIT. It adds 1,253 tokens to every session, about $0.0050 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 2026-09-01.
loseit-mcp-local AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| loseit-mcp-local AGENTS.mdthe-mace/loseit-mcp-local | Instructions file | 0 | 2d ago | MIT | A | 1,253 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,685 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | 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 |