Borrowing it
Nothing to install: this file belongs to Whamp/pi-token-burden. 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/Whamp/pi-token-burden/main/AGENTS.mdgit clone --depth 1 https://github.com/Whamp/pi-token-burdenWrote 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/whamp/pi-token-burden/agents-md)<a href="https://agentmods.dev/instructions/whamp/pi-token-burden/agents-md"><img src="https://agentmods.dev/badge/instructions/whamp/pi-token-burden/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/whamp/pi-token-burden/agents-md"><img src="https://agentmods.dev/badge/instructions/whamp/pi-token-burden/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 | $0.00447 | $0.00447 |
| Opus 5.5 | $0.00179 | $0.00179 |
| Sonnet 5.5 | $0.00089 | $0.00089 |
| Haiku 4.5 | $0.00045 | $0.00045 |
Grade A, and why
pi-token-burden 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 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.
How it starts
The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pi-token-burden
A pi extension that measures model-facing prompt and tool-schema tokens and presents the breakdown in the /token-burden TUI.
Verification
- Inspect the nearest tests before changing behavior and add or adjust coverage appropriate to the change.
- Run focused checks while working, then run
pnpm run checkbefore committing. - For user-visible extension changes, also run
pi -e ./src/index.tsand exercise the changed flow. - For documentation-only changes, verify every path, command, and claim against the repository.
Work is complete when each requirement is backed by passing command output or an exercised interface.
When blocked, use 1-3-1: state one problem, three options, and one recommendation, then wait for Will before implementing an option.
Context pointers
- Architecture and decisions: use
napkin search "<topic>"andnapkin read "<note>". Readguides/Napkin Workflow.mdbefore writing durable project knowledge. Napkin records why; git records diffs. - Domain language: read
docs/agents/domain.mdbefore codebase exploration, architectural work, or introducing terminology. Use the vocabulary inCONTEXT.md. - Issues and pull requests: read
docs/agents/issue-tracker.mdbefore GitHub operations. For triage, also readdocs/agents/triage-labels.mdbefore applying labels. - Commands: treat
package.jsonscripts as the command source of truth.pnpm run test:e2erequires tmux;pnpm run checkis the pre-commit gate.
Change boundaries
Get Will's approval before:
- adding a dependency;
- registering a tool that executes shell commands;
- changing lint rules.
Keep TypeScript free of any; model values with precise types and TypeBox schemas at runtime boundaries. Keep credentials outside the repository. Generate CHANGELOG.md through the package scripts.
When instructions conflict, requirements change, architecture shifts, or project documentation is inaccurate, surface the mismatch and propose the relevant rules, domain, or napkin update. Wait for confirmation before making that documentation change.
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.
- 2mo ago First seen · 34 lines · 447 tokens per session scan A 1f8c4cb4982a
pi-token-burden AGENTS.md is an instructions file published in the GitHub repository Whamp/pi-token-burden (54 stars, last pushed 29d ago), licensed MIT. It adds 447 tokens to every session, about $0.0018 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.
pi-token-burden AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| pi-token-burden AGENTS.mdWhamp/pi-token-burden | Instructions file | 54 | 29d ago | MIT | A | 447 | Codex, OpenCode |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |