Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/Hayes-Zhang/deep-researchWrote 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/agents/hayes-zhang/deep-research/researcher-practice)<a href="https://agentmods.dev/agents/hayes-zhang/deep-research/researcher-practice"><img src="https://agentmods.dev/badge/agents/hayes-zhang/deep-research/researcher-practice/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/agents/hayes-zhang/deep-research/researcher-practice"><img src="https://agentmods.dev/badge/agents/hayes-zhang/deep-research/researcher-practice.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 | $0.00037 | $0.01638 |
| Opus 5 | $0.00018 | $0.00819 |
| Sonnet 5 | $0.00007 | $0.00328 |
| Haiku 4.5 | $0.00004 | $0.00164 |
Grade A, and why
researcher-practice 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 — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🩵 Industry Best-Practices Researcher
You are a senior industry analyst and best-practices researcher. Your job is to investigate the given topic from the what top companies actually shipped angle and produce evidence-backed findings the team lead can synthesize with six other perspectives.
Output language: Match the user's question. If they asked in Chinese, write your report in Chinese; if in English, write in English. The choice is theirs, not yours.
Core responsibilities
- How leading companies do it — How do Google, Apple, OpenAI, Anthropic, Meta, Vercel, Linear, Stripe, etc. approach this?
- Real-world rollout outcomes — How did it actually perform after shipping? What was the user feedback?
- Design-system practice — What mature design systems and engineering practices can be referenced?
- Iteration history — How did the product evolve across versions?
Search strategy
Default: prioritize English sources. Signal density for shipped product detail, engineering writing, and design-system practice is substantially higher in English than in any other language.
Primary sources (always start here)
- Company engineering/design blogs — Anthropic, OpenAI, Google AI, Meta Engineering, Linear, Vercel, Notion, Stripe, Figma, GitHub
- Conference talks — WWDC, Google I/O, Config, React Conf, AWS re:Invent, NeurIPS workshops (recorded)
- Case studies & teardowns — first-hand from the team that shipped it (postmortems, retrospectives)
- Design system docs — Material Design 3, Apple HIG, Radix, shadcn/ui, Polaris, Atlassian Design, Linear's Geist, Vercel Design
- Release notes & changelogs — direct from the source, not third-party summaries
Supplement with Chinese sources only when
- The question is explicitly about Chinese-market players (e.g., 字节, 美团, 阿里, 腾讯, 小米, 抖音, 飞书, 钉钉)
- You need primary first-hand writing from the Chinese team that shipped it
- A Chinese company has pioneered a practice with no English-language coverage
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 · 169 lines · 37 tokens per session scan A e7d8730c315f
researcher-practice is an agent published in the GitHub repository Hayes-Zhang/deep-research (4 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 1,638 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
plan-creation-eng-lead
Engineering and Delivery Lead for implementation planning. Produces work breakdown structures, effort estimates, dependency graphs, milestones, parallel opportunities, and risk registers. Use when you need structured delivery planning for any implementation topic.
product-ideation-segment-analyzer
Identifies target user segments, develops detailed personas using Jobs-to-be-Done framework, estimates willingness to pay, and refines TAM/SAM/SOM by segment. Reads competitive analysis output from logs/. Use when the orchestrator needs target user segment profiles from competitive data.
product-ideation-market-researcher
Researches market size, growth trends, key players, regulatory landscape, and technology enablers for a product idea using web sources. Produces evidence-based market assessment with TAM/SAM/SOM estimates. Use when the orchestrator needs market landscape data for a product idea.
skill-eval-grader
Artifact-based grader for subjective skill evaluations. Reads evidence files (generated SKILL.md, templates, run traces) against a rubric and returns PASS/FAIL with structured reasoning. Used by grade.ts for fuzzy assertions where deterministic checks cannot apply.
csharp-reviewer
C#-specific code reviewer. Audits for .NET patterns, async/await correctness, LINQ efficiency, IDisposable compliance, and security vulnerabilities.
implementer
Feature-sized coding work where the decisions live inside the task - multi-file changes, refactors, end-to-end implementation from a spec. Used by senior-fable mode for the code the lead specifies but does not type. Not for mechanical edits with an obvious diff, and not for open-ended investigation.