Borrowing it
Nothing to install: this file belongs to rjmurillo/ai-agents. 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/rjmurillo/ai-agents/main/.github/instructions/token-economy.instructions.mdgit clone --depth 1 https://github.com/rjmurillo/ai-agentsWrote 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/rjmurillo/ai-agents/token-economy)<a href="https://agentmods.dev/instructions/rjmurillo/ai-agents/token-economy"><img src="https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/token-economy/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/rjmurillo/ai-agents/token-economy"><img src="https://agentmods.dev/badge/instructions/rjmurillo/ai-agents/token-economy.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 | $0.00413 | $0.00413 |
| Opus 5 | $0.00206 | $0.00206 |
| Sonnet 5 | $0.00083 | $0.00083 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
ai-agents token-economy.instructions.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.
What it actually says
Token Economy
Rework is the expensive path: a wrong edit bills the edit, the review, the fix, and the re-review. Reading the governing rule and the exact span you are about to change costs less than any one of those four.
Never trade a gate, a test, or evidence in a report for tokens. That buys a cheap turn now and a full rework cycle later.
Why this rule is scoped rather than always-on
It is deliberately not paths: ["**"], for two reasons worth stating so nobody "fixes" the scope later.
The always-on corpus is closed. The instruction-budget validator measures the generated mirrors whose glob matches every file of a language, and the Python baseline sits within its 600-byte reserve of the ceiling. An always-on copy of this rule would have to be funded by cutting other always-on content, and the rule-audit procedure in the context-optimizer skill requires replicated eval runs on two models after any always-on change, a cut and an addition alike. This rule carries no such evidence and does not claim to.
It also fails that procedure's admission test for always-on content, on two of three criteria: the model already knows that rework is expensive, and the tactics are retrievable on demand from the LSP-first, search-before-building, and voice rules and from the GitHub URL intercept skill. What is left is the framing above, which is cheap to load where it applies.
The globs are the gated trees that also exist in a consumer install: agent configuration, governance, workflows, and tests. Those are where a wrong edit costs a CI cycle. The upstream-only build and scripts trees are deliberately absent from the list, because a shipped rule scoped to a tree the consumer does not have is dead weight in every install. None of these globs matches every file of any language, so this rule adds nothing to the always-on language baselines.
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.
- 5d ago First seen · 20 lines · 413 tokens per session scan A 40cf5383bb50
ai-agents token-economy.instructions.md is an instructions file published in the GitHub repository rjmurillo/ai-agents (45 stars, last pushed today), licensed MIT. It adds 413 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 2026-09-03.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.