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.
npx agentmods add instructions/851-labs/tokenmaxxing/agents-mdgit clone --depth 1 https://github.com/851-labs/tokenmaxxingWhat 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 | $0.00438 | $0.00438 |
| Opus 5 | $0.00219 | $0.00219 |
| Sonnet 5 | $0.00088 | $0.00088 |
| Haiku 4.5 | $0.00044 | $0.00044 |
Grade A, and why
tokenmaxxing 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 3d 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.
What it actually says
Repository Instructions
Effect Error Style
- Prefer native Effect errors over plain JavaScript
Errorsubclasses in Effect code. - Use
Data.TaggedErrorfor internal typed errors that stay inside the Effect error channel. - Use
Schema.TaggedErrorClasswhen an error is part of a public schema or wire contract. - Avoid
throwfor expected domain failures; returnEffect.fail(...)with a typed error instead.
Export Style
- Prefer local declarations first and grouped exports at the end of each authored source file.
- Use
export { ... }for runtime values andexport type { ... }for type-only exports. - Put default exports at the end too, using a named local value before
export default name;. - Do not hand-edit generated files just to satisfy this style rule.
Conventions
- Daily usage rows are keyed
(deviceId, date, source, model)and upserted; sync must stay idempotent. datecolumns are opaqueYYYY-MM-DDstrings (ccusage local-time buckets); never parse them into Date objects for bucketing.- CLI tokens (
tmx_prefix) never expire; revocation (revokedAt) is the only kill switch.
CLI Output Style
- Foreground human CLI commands should wrap async work in
humanSpinnerinsidehumanFrame. This includes network calls, filesystem writes, subprocesses, scheduler changes, package-manager updates, browser opens, and other operations that can visibly pause. - Keep machine output clean:
--json,silent, and scheduled/background service paths must not emit spinners or decorative human logs. - Prefer shared output helpers (
humanFrame,humanSpinner,humanLog,formatUrl,formatHighlight,writeJson) over rawconsoleoutput in foreground commands. - Spinner rows should resolve into the final success or error row for that operation instead of adding a separate duplicate row.
- Do not use indefinite spinners while waiting for external user action; show the actionable URL/code/instruction and then wait quietly.
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.
- 3d ago First seen · 36 lines · 438 tokens per session scan A 525f14f2ec16
tokenmaxxing AGENTS.md is an instructions file published in the GitHub repository 851-labs/tokenmaxxing (67 stars, last pushed 27d ago), licensed MIT. It adds 438 tokens to every session, about $0.0022 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.
Other instructions, from other repositories
opensrc AGENTS.md
Instructions for vercel-labs/opensrc, covering agents.md, monorepo structure, cli (packages/opensrc), docs (apps/docs) and releasing.
nanocoder CLAUDE.md
Claude Code instructions for Nano-Collective/nanocoder, covering claude.md, development commands, build and run, testing (run before committing) and individual test commands.
nanocoder AGENTS.md
AGENTS.md instructions for Nano-Collective/nanocoder, covering agents.md, project overview, architecture, key files and development commands.
vibe-coding-repository-standard AGENTS.md
Instructions for cz1993/vibe-coding-repository-standard, covering vcrs repository instructions, purpose, communication, change discipline and privacy and safety.
hunch CLAUDE.md
Instructions for davesheffer/hunch, covering claude.md, what this is, commands, architecture and 🧠 hunch (engineering memory).
hunch copilot-instructions.md
Instructions for davesheffer/hunch, covering copilot instructions, 🧠 hunch (engineering memory) and ⛔ top invariants (do not break).