Borrowing it
Nothing to install: this file belongs to powerofjinbo/phdtaketaketake. 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/powerofjinbo/phdtaketaketake/main/AGENTS.mdgit clone --depth 1 https://github.com/powerofjinbo/phdtaketaketakeWrote 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/powerofjinbo/phdtaketaketake/agents-md)<a href="https://agentmods.dev/instructions/powerofjinbo/phdtaketaketake/agents-md"><img src="https://agentmods.dev/badge/instructions/powerofjinbo/phdtaketaketake/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/powerofjinbo/phdtaketaketake/agents-md"><img src="https://agentmods.dev/badge/instructions/powerofjinbo/phdtaketaketake/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 | $0.00697 | $0.00697 |
| Opus 5 | $0.00349 | $0.00349 |
| Sonnet 5 | $0.00139 | $0.00139 |
| Haiku 4.5 | $0.00070 | $0.00070 |
Grade A, and why
phdtaketaketake 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 9d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
phdtaketaketake — agent instructions
This file is the entry point that OpenAI Codex (and other agents that
discover persistent instructions via AGENTS.md per the Codex
convention) uses to find this skill. It is intentionally a short
pointer, not a copy of SKILL.md. Maintaining two copies of the
skill contract creates drift; the canonical contract lives in
SKILL.md, and Cursor / Codex / any future host reads
that file or gets a generated short-pointer like this one.
Use
When the user asks about PhD advisor matching, application triage,
PI ranking, connection-first evaluation, evidence-backed application
strategy, or PhD-application CV optimization, follow the workflow
defined in SKILL.md:
- Workflow A (advisor matching): Steps 1–8.5 — gather profile, generate discovery plan, find candidates, compute connection edges, score with the 5-layer pipeline (CAPEG → application_strength → risk_adjusted → difficulty_adjusted → strategy bucket), present cards.
- Workflow B (CV optimization): Steps CV-1–CV-6 — read the
bundled LaTeX template, fill from user-typed input, optionally
reorder for a target PI from
match.json, compile.
Hard rules (non-negotiable for both workflows)
- Connection-first —
w_C > w_Ain every tier. Verified academic network beats h-index. - Evidence-first — every claim traces to a real source the agent actually fetched. Four-state semantics: Verified / Verified-empty / Missing / Blocked. Strict mode rejects unsourced claims.
- No invention — never fabricate candidate facts, advisor connections, publication records, GPA conversions, opportunity signals, CV experiences, papers, or skills.
- CV source-of-truth — every fact in the rendered
cv.textraces to something the user explicitly provided in conversation. Target PIs frommatch.jsondrive ordering decisions; their names never appear in the CV body. - Output is a relative-fit index, not an admission probability. Surface what's strong, what's weak, what's uncertain — never claim a numeric admit chance.
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.
- 9d ago First seen · 61 lines · 697 tokens per session scan A 8e5e49f47366
phdtaketaketake AGENTS.md is an instructions file published in the GitHub repository powerofjinbo/phdtaketaketake (32 stars, last pushed 2mo ago), licensed MIT. It adds 697 tokens to every session, about $0.0035 per session on Opus 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.
Other instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.