Borrowing it
Nothing to install: this file belongs to haruhisa-enomoto/math-research-harness. 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/haruhisa-enomoto/math-research-harness/main/AGENTS.mdgit clone --depth 1 https://github.com/haruhisa-enomoto/math-research-harnessWrote 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/haruhisa-enomoto/math-research-harness/agents-md)<a href="https://agentmods.dev/instructions/haruhisa-enomoto/math-research-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/haruhisa-enomoto/math-research-harness/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/haruhisa-enomoto/math-research-harness/agents-md"><img src="https://agentmods.dev/badge/instructions/haruhisa-enomoto/math-research-harness/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 | $0.02489 | $0.02489 |
| Opus 5.5 | $0.00996 | $0.00996 |
| Sonnet 5.5 | $0.00498 | $0.00498 |
| Haiku 4.5 | $0.00249 | $0.00249 |
Grade A, and why
math-research-harness 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 13d 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 — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Session contract
This repository supports owner-directed mathematical research. Infer scope and authorization from ordinary conversation. Do not ask the owner to operate the harness as a configuration system. The sample thread and files explicitly marked as tutorial or fictional examples demonstrate record shape only; they are not canonical mathematical state.
Boot
Read this file first and classify the task.
- Meta or repository work needs no mathematical thread state.
- For mathematical work, read
STEERING.mdand the relevantthreads/<thread>/LEDGER.md. Readdocs/PROJECT-FOUNDATIONS.mdonly when the ledger cites it, the task spans several threads, or one of its shared conventions is genuinely load-bearing; use it then without rederiving its contents or presenting them as new. - If the thread has
RESEARCH-QUESTIONS.md, it runs the question-driven variant indocs/RESEARCH-MODES.md: read that document and the question list whole before choosing work, and followdocs/RECORDS.md's list rules. OrdinaryQUESTIONS.mdfiles are catalogs or general question lists; their presence does not select a research mode or trigger the hooks. - Read
threads/INDEX.mdonly when the thread is unclear or the task concerns the thread directory. - Follow ledger citations only as the task needs them. Do not load every note or claim by default.
- For literature work, also read
docs/LITERATURE.md. - For a manuscript citation, attribution, or related-literature audit, also
read
docs/CITATION-AUDIT.md. “Do citation audit for ” invokes its full scope, including missing precedents and proof-method credit. - For backend-dependent work, a durable computation, or a counterexample, read
docs/COMPUTATIONS.md. - For collaboration with agents lacking repository access, read
docs/COLLABORATION.md. - Read
docs/CAMPAIGN-CONTRACT.mdbefore an exact full-resolution campaign. - Read
docs/REPORTS.mdbefore producing a substantial owner-facing report. - Before drafting or revising a live research-paper manuscript, use
write-research-paper(orpolish-math-prosewhen polishing prose and proof presentation or repairing post-polish math-audit findings) and readdocs/PAPER-WRITING.mdfor this repository's local overlay. - Before supervising a first-reader review, read
docs/FIRST-READER-REVIEW.md; the isolated reader loads the portable protocol throughread-research-paper. - Before supervising a skeptical-editor review, read
docs/SKEPTICAL-EDITOR-REVIEW.md; the isolated editor loads the portable protocol throughread-research-paper.
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.
- 13d ago Changed · -40 lines · -325 tokens per session cc8c14623cef
- 2mo ago First seen · 258 lines · 2,814 tokens per session scan A 99a30448e0cc
math-research-harness AGENTS.md is an instructions file published in the GitHub repository haruhisa-enomoto/math-research-harness (16 stars, last pushed 14d ago), licensed MIT. It adds 2,489 tokens to every session, about $0.0100 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.
math-research-harness AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| math-research-harness AGENTS.mdharuhisa-enomoto/math-research-harness | Instructions file | 16 | 14d ago | MIT | A | 2,489 | 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 | yesterday | 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 |