Borrowing it
Nothing to install: this file belongs to chenmingtang830/proofpress. 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/chenmingtang830/proofpress/main/AGENTS.mdgit clone --depth 1 https://github.com/chenmingtang830/proofpressWrote 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/chenmingtang830/proofpress/agents-md)<a href="https://agentmods.dev/instructions/chenmingtang830/proofpress/agents-md"><img src="https://agentmods.dev/badge/instructions/chenmingtang830/proofpress/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/chenmingtang830/proofpress/agents-md"><img src="https://agentmods.dev/badge/instructions/chenmingtang830/proofpress/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 | $0.06095 | $0.06095 |
| Opus 5.5 | $0.02438 | $0.02438 |
| Sonnet 5.5 | $0.01219 | $0.01219 |
| Haiku 4.5 | $0.00609 | $0.00609 |
Grade A, and why
proofpress 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project instructions
Default: hosted governed context
For durable agent-produced knowledge, use the proofpress-governed-context
skill. It is the default governance path for this repository; Markdown, HTML,
and source-code changes do not require artifact-ledger capture or snapshotting.
When operating from another repository, install this repository's
proofpress-governed-context skill before connecting MCP. Use the
client-specific installation commands in docs/REMOTE_MCP.md. MCP supplies the
tool surface, while the skill supplies the required governance workflow.
Before relying on prior knowledge, retrieve only eligible, in-scope governed context and preserve its limits. For a durable decision, evidence-backed claim, reproducible experiment result, integration contract, or incident learning, submit a bounded proposal with evidence and report its receipt.
An agent may propose and evaluate but may never approve its own proposal, use owner or recovery credentials, upload secrets or raw private traces, or claim that a candidate is governed context before authorized human approval.
Optional: portable artifact ledger
Use proofpress legacy only when the user explicitly asks for a portable,
offline-verifiable artifact history or when receiving a portable artifact for
inspection or import. Existing artifact histories, anchors, and capsules are
preserved; do not remove or rewrite them merely because this is no longer the
default workflow.
For an explicitly selected portable artifact, run capture before editing an
existing target; then read its policy, preserve native anchors, write honest
claims for touched blocks, snapshot with explicit actors and a real reason, and
run verify. Do not use the legacy ledger for source code, routine documents,
or the governed-context skill.
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 Changed · -1 tokens per session d5c7fa31e28b
- 2mo ago Changed · +22 lines · +2,378 tokens per session bac669cd1557
- 2mo ago First seen · 43 lines · 3,718 tokens per session scan A 9331e14b05aa
proofpress AGENTS.md is an instructions file published in the GitHub repository chenmingtang830/proofpress (20 stars, last pushed 2d ago), licensed Apache-2.0. It adds 6,095 tokens to every session, about $0.0244 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 2026-08-31.
proofpress AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| proofpress AGENTS.mdchenmingtang830/proofpress | Instructions file | 20 | 2d ago | Apache-2.0 | A | 6,095 | 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 |