toktrack AGENTS.md

toktrack AGENTS.md is an instructions file for Codex, OpenCode from mag123c/toktrack. It costs 416 tokens per session, scanned A, original, MIT.

Repository instructions for AI coding agents, covering project context, rules for handling failures, test-driven development, checks, and commits.

In plain words
What is it for?
Use it as a starting guide before changing the repository, especially when loading data, handling errors, writing tests, running checks, or committing code.
Why use it?
It prevents agents from missing project-specific requirements, such as writing a test before implementation and continuing when an optional data source fails.

Instructions file for CodexOpenCode

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/mag123c/toktrack/agents-md
Clone the repo
git clone --depth 1 https://github.com/mag123c/toktrack

Made for: Codex, OpenCode.

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 toktrack AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mag123c/toktrack/agents-md.svg)](https://agentmods.dev/instructions/mag123c/toktrack/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mag123c/toktrack/agents-md"><img src="https://agentmods.dev/badge/instructions/mag123c/toktrack/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 416 This file is loaded in full into every session.
When invoked 416 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00416 $0.00416
Opus 5 $0.00208 $0.00208
Sonnet 5 $0.00083 $0.00083
Haiku 4.5 $0.00042 $0.00042

Measured 5d ago against content hash 179bc4266611, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

toktrack 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 5d 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.

AGENTS.md · 38 lines

What it actually says

AGENTS.md

Guidance for any AI coding agent (Codex, Claude, Cursor, …) working in this repo. This file is intentionally tool-agnostic. The canonical project context lives in:

Read those first. The notes below are the few things most easily missed.

Non-obvious rules

  • Degrade gracefully on partial failure. DataLoaderService aggregates many independent sources; one source failing must never abort the whole load. Warn and continue. Optional/remote sources should fall back to their last good snapshot. A source the user selected explicitly may fail loudly, but one pulled in implicitly (a configured default) must not break a plain command. See the "Data Loading" section in conventions.md.
  • Errors use ToktrackError, not anyhow, in library code.
  • Comments and test names are English only. (Private .dev/ docs are exempt.)
  • TDD: no implementation without a test first (RED → GREEN → REFACTOR).

Before you finish

make check    # fmt + clippy + test — must pass before committing

Commits

{type}({scope}): {description}

types: feat|fix|refactor|docs|test|chore|perf · scopes: parser|tui|services|cache|cli

Do not add AI/agent attribution lines (no Co-Authored-By for the agent) to commits.

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. 5d ago First seen · 38 lines · 416 tokens per session scan A 179bc4266611

Subscribe to this mod's changes

toktrack AGENTS.md is an instructions file published in the GitHub repository mag123c/toktrack (188 stars, last pushed yesterday), licensed MIT. It adds 416 tokens to every session, about $0.0021 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 2026-08-30.