Borrowing it
Nothing to install: this file belongs to Chip-G0202/PaperEcho. 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/Chip-G0202/PaperEcho/main/AGENTS.mdgit clone --depth 1 https://github.com/Chip-G0202/PaperEchoWrote 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/chip-g0202/paperecho/agents-md)<a href="https://agentmods.dev/instructions/chip-g0202/paperecho/agents-md"><img src="https://agentmods.dev/badge/instructions/chip-g0202/paperecho/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/chip-g0202/paperecho/agents-md"><img src="https://agentmods.dev/badge/instructions/chip-g0202/paperecho/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 | $0.15478 | $0.15478 |
| Opus 5.5 | $0.06191 | $0.06191 |
| Sonnet 5.5 | $0.03096 | $0.03096 |
| Haiku 4.5 | $0.01548 | $0.01548 |
Grade A, and why
PaperEcho 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 2d 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 — 733 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Medical Literature Workflow Agent Reference
General Execution Environment And Permission Boundaries
- Default to completing tasks within the current repository/workspace.
- Recommended sandbox permission is Workspace write.
- Use Read only mode for auditing and planning work.
- Full access is a temporary exception only. Before requesting it, report exact paths, reason, scope of impact, risk, and rollback method, then wait for user approval.
- Keep project files, generated artifacts, temporary files, and test outputs inside the workspace.
- Prefer workspace runtime, project-local configuration, or standard user-level cache directories for Node, dependencies, and caches.
- Do not access, copy, index, or expose unrelated sensitive paths, including SSH private keys, browser data, Desktop, Downloads, personal Documents, or system configuration directories.
- Before network access, dependency installation, Zotero access, external API calls, global configuration changes, or reading/writing files outside workspace, report exact commands, necessity, impact scope, rollback availability, and whether a workspace-local alternative exists, then wait for approval.
- Before each major modification round, run
git status --short; if the working tree is not clean, report existing changes first. - Suggest creating a branch before large or high-risk modifications.
- Never reset, checkout, clean, delete, or overwrite existing user changes without explicit permission.
- If
node/npm/pythonor other runtimes are not executable or lack permission, classify as an environment failure, not a business test failure. - Prioritize diagnosing
PATHand runtime paths, and prioritize workspace-provided or project-approved runtimes. Do not request Full access only because one path is not executable.
Goal
Operate a weekly medical literature pipeline with parallel entry channels:
- RSS ingestion
- PubMed/PMC retrieval via direct NCBI requests in the scripts
Then run unified dedup, triage, Zotero writeback, translation backfill, and workbook export in the existing Research OS structure.
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.
- 2d ago Changed · +21 lines · +1,373 tokens per session 86e212dc828b
- 1mo ago Changed · +5 lines · +311 tokens per session e21ef02c8a26
- 2mo ago First seen · 707 lines · 13,794 tokens per session scan A 2213f85a3dca
PaperEcho AGENTS.md is an instructions file published in the GitHub repository Chip-G0202/PaperEcho (76 stars, last pushed 3d ago), licensed MIT. It adds 15,478 tokens to every session, about $0.0619 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.
PaperEcho AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| PaperEcho AGENTS.mdChip-G0202/PaperEcho | Instructions file | 76 | 3d ago | MIT | A | 15,478 | 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 |