suuntool: Instructions file for Claude Code

CLAUDE.md

suuntool CLAUDE.md is an instructions file for Claude Code from tajchert/suuntool. It costs 4,299 tokens per session, scanned A, original, MIT.

A developer guide for suuntool, a Go command-line program that accesses the unofficial Suunto and Sports-Tracker web API. It explains the project structure, design rules, and available commands.

In plain words
What is it for?
Use it when adding or changing commands, working with authentication and API output, or understanding the repository's internal reference material and layout.
Why use it?
It gives developers and coding agents the project context needed to make changes that fit its one-way architecture and terminal-based use.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md.

This is tajchert/suuntool's own configuration. It tells Claude Code how to work on suuntool 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 suuntool configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tajchert/suuntool. 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/tajchert/suuntool/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/tajchert/suuntool

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 suuntool CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tajchert/suuntool/claude-md/github.svg)](https://agentmods.dev/instructions/tajchert/suuntool/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/tajchert/suuntool/claude-md"><img src="https://agentmods.dev/badge/instructions/tajchert/suuntool/claude-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.

agentmods 80×15 button for suuntool CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tajchert/suuntool/claude-md"><img src="https://agentmods.dev/badge/instructions/tajchert/suuntool/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 4,299 This file is loaded in full into every session.
When invoked 4,299 The same file — it is already loaded in full.
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 $0.04299 $0.04299
Opus 5.5 $0.01720 $0.01720
Sonnet 5.5 $0.00860 $0.00860
Haiku 4.5 $0.00430 $0.00430

Measured 2mo ago against content hash fdf0e6fde063, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

suuntool CLAUDE.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 2mo 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.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — developer orientation

Audience: senior engineers (and LLM agents) joining this repo. Read this once, then read the code.

What this is

suuntool is a Go CLI for the unofficial Suunto / Sports-Tracker HTTP API. It is meant to be used by humans and by agents driving a terminal — every UX decision flows from that dual audience.

Internal reference material (endpoint inventory, signing scheme, Python reference client, golden-vector diagnostics) lives in handoff/. That directory is excluded via .git/info/exclude — not .gitignore — so it stays local but is never committed. Treat it as load-bearing reference material; don't delete it.

Layering — strict, one-way

main.go
└── cmd/                 Cobra commands. Knows about session+api+output, nothing else.
    ├── root.go          persistent flags, exit codes, helpers (baseURL, authedClient, emit, pickTimeout, parseSince, useTTYColor)
    ├── login.go logout.go whoami.go profile.go doctor.go endpoints.go version.go
    ├── workouts.go      workouts list/get/count/stats/sml/fit/export/comments/react/edit/upload/delete (+ --summary, --stream, --since)
    ├── guides.go        guides list/download/upload/update/pin/unpin/priority/delete (+ --yes). Transport only — no guide.json parsing.
    ├── wellness.go      wellness sleep/activity/recovery/sleepstages NDJSON streams
    ├── wellness_sleep_pretty.go   TTY-only sleep table renderer (writeSleepFooter)
    ├── mcp.go           `suuntool mcp` stdio MCP server entry (--allow-write / --allow-destructive)
    └── login_test.go, root_test.go, wellness_sleep_pretty_test.go    end-to-end via httptest
internal/
├── auth/                signing pipeline. Zero net/http imports.
│   ├── keys.go          embedded signing constants (login parts, TOTP parts, package name, user-agent)
│   ├── obfuscator.go    KeyObfuscator XOR + lossy-UTF-8 replace; DeriveLoginSecret / DeriveTOTPMasterSecret
│   ├── totp.go          PBKDF2-HmacSHA1 + RFC 6238 HOTP → GenerateTOTP(salt, offsetMS)
│   └── signer.go        SignParams(path, []Param) → base64url(SHA-256), RandomSalt, NowMS
├── api/                 HTTP transport.
│   ├── client.go        Client + Do()/DoStream() — injects STTAuthorization + User-Agent, maps HTTP status → typed errors, transparent gzip
│   ├── envelope.go      generic AskoResponse[T] + DecodeAsko[T]
│   ├── errors.go        *Error{Code, Message, Hint, HTTP, Exit} — ExitCode() drives os.Exit
│   └── endpoints/       per-resource wrappers — add a file here for each new resource
│       ├── session.go   Login (POST /login2), Logout, RemoteUserSession + Pretty()
│       ├── user.go      Whoami, Settings, Follow, UserByName + Prettier impls
│       ├── workouts.go  List/Get/Count/Stats/SML/FIT/Delete + WorkoutList.Summary / SummaryWithWoW
│       ├── comments.go reactions.go edit.go share.go extensions.go upload.go   workout writes (x-totp via cmd layer)
│       ├── guides.go    List/Download/Create/Update/Delete/SetGuidePinned/GuidePriority — raw zip body, no x-totp, no guide.json parsing (see the file's own package doc)
│       ├── wellness.go  NDJSON stream decoders (sleep/activity/recovery/sleepstages)
│       ├── format.go    formatKm / formatDuration / renderTable(Styled) shared by Pretty()
├── session/             session.go — XDG-aware persistence, 0600 perms, ErrNoSession (+ TOTPHeaders helper)
├── output/              the single render boundary
│   ├── output.go        Render / RenderToFile, Opts, Prettier interface, resolveFormat
│   └── tty.go           IsStdoutTTY (respects NO_COLOR)
└── mcp/                 Model Context Protocol adapter (stdio server)
    ├── server.go        Run(ctx, Opts), registerAll, deps (api.Client + session)
    ├── registry.go      tier + toolRegistrar shape; per-tool registrars elsewhere
    ├── tools_read.go    read-tier registrars (whoami, profile_*, workouts_*, wellness_*, doctor, activity_type_name, guides_list, guides_download, guides_priority)
    ├── tools_write.go   --allow-write registrars (comment, react, edit, batch_update, share, extensions, upload, guides_upload, guides_update, guides_pin, guides_unpin)
    ├── tools_destructive.go  --allow-destructive registrars (delete, uncomment, unreact, guides_delete)
    ├── activity.go      activityId → activityName enrichment shared by workouts_list/get/stats
    └── errors.go        mapError / mapErrorToCallToolResult (preserves *api.Error structure for the LLM)

Read the full file on GitHub · 136 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. 2mo ago First seen · 136 lines · 4,299 tokens per session scan A fdf0e6fde063

Subscribe to this mod's changes

suuntool CLAUDE.md is an instructions file published in the GitHub repository tajchert/suuntool (32 stars, last pushed 2mo ago), licensed MIT. It adds 4,299 tokens to every session, about $0.0172 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.

Related

suuntool CLAUDE.md compared with instructions from other repositories

suuntool CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
suuntool CLAUDE.mdtajchert/suuntoolInstructions file322mo agoMITA4,299Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143kyesterdayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149kyesterdayMITA4,680Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA5,516GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195kyesterdayMITA3,093GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file274k2d agoMITA4,313Codex, OpenCode