Borrowing it
Nothing to install: this file belongs to heleninsights-dot/phd-deepread-workflow. 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/heleninsights-dot/phd-deepread-workflow/main/AGENTS.mdgit clone --depth 1 https://github.com/heleninsights-dot/phd-deepread-workflowWrote 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/heleninsights-dot/phd-deepread-workflow/agents-md)<a href="https://agentmods.dev/instructions/heleninsights-dot/phd-deepread-workflow/agents-md"><img src="https://agentmods.dev/badge/instructions/heleninsights-dot/phd-deepread-workflow/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/heleninsights-dot/phd-deepread-workflow/agents-md"><img src="https://agentmods.dev/badge/instructions/heleninsights-dot/phd-deepread-workflow/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 | $0.01335 | $0.01335 |
| Opus 5.5 | $0.00534 | $0.00534 |
| Sonnet 5.5 | $0.00267 | $0.00267 |
| Haiku 4.5 | $0.00134 | $0.00134 |
Grade C, and why
phd-deepread-workflow AGENTS.md scanned grade C with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- Ubuntu/Debian: `sudo apt install -y tesseract-ocr` Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
ls <SKILLS_DIR>phd-deepread/SKILL.md # ~/.claude/skills/... or ~/.codex/skills/... How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Install instructions for AI agents
This file tells an AI coding agent (e.g. Claude Code or Codex) how to install and verify the phd-deepread workflow on the user's machine. The user is non-technical and will trust you to run these steps end-to-end. Do not ask the user to type terminal commands themselves; execute them yourself and report results.
If anything in this file conflicts with the README, follow this file — the README is written for humans skimming, this is the executable spec.
Detect which agent you are (paths differ)
This workflow installs as a skill, and each agent keeps skills in a different directory. Determine yours first and use it everywhere below as <SKILLS_DIR>:
| Agent | <SKILLS_DIR> |
|---|---|
| Claude Code | ~/.claude/skills/ |
| Codex | ~/.codex/skills/ |
So the installed skill lives at <SKILLS_DIR>phd-deepread/. If you can't tell which agent you are, check which directory exists.
Prerequisites — confirm before installing
Before any install, confirm the user has both:
- A skill-capable AI coding agent — this workflow runs inside Claude Code or Codex. If the user has neither, point them to claude.ai/code (Claude Code) or the Codex CLI and stop here.
- Obsidian — the final output is a JSON canvas file that only renders in Obsidian. Without Obsidian, the user cannot visualize the paper. Point them to obsidian.md.
If the user only wants AI help reading a PDF, they don't need this tool — just drag the PDF into any AI chat and ask questions directly. This workflow is for people who want structured literature notes and a critical-thinking canvas in Obsidian.
Goal
After install, all of the following must succeed:
- The
phd-deepreadcommand runs from any directory. phd-deepread doctorreports core dependencies as OK.- The skill is available in your agent (Claude Code or Codex), installed at
<SKILLS_DIR>phd-deepread/.
The end-to-end value: extract a PDF → Claude generates a structured literature note → the user opens a 9-node critical-thinking canvas in Obsidian to visualize the 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.
- 2mo ago First seen · 128 lines · 1,335 tokens per session scan C d54982a1dc8a
phd-deepread-workflow AGENTS.md is an instructions file published in the GitHub repository heleninsights-dot/phd-deepread-workflow (64 stars, last pushed 4mo ago), licensed MIT. It adds 1,335 tokens to every session, about $0.0053 per session on Opus 5.5. A static security scan graded it C with 2 findings (asks for root, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
phd-deepread-workflow AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| phd-deepread-workflow AGENTS.mdheleninsights-dot/phd-deepread-workflow | Instructions file | 64 | 4mo ago | MIT | C | 1,335 | 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 |