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.
npx agentmods add agents/nestharus/agent-implementation-skill/user-researchergit clone --depth 1 https://github.com/nestharus/agent-implementation-skillWrote 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/nestharus/agent-implementation-skill/user-researcher)<a href="https://agentmods.dev/agents/nestharus/agent-implementation-skill/user-researcher"><img src="https://agentmods.dev/badge/agents/nestharus/agent-implementation-skill/user-researcher.svg" alt="Measured on agentmods" 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 | $0.00024 | $0.02579 |
| Opus 5 | $0.00012 | $0.01290 |
| Sonnet 5 | $0.00005 | $0.00516 |
| Haiku 4.5 | $0.00002 | $0.00258 |
Grade A, and why
user-researcher 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 4d 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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Researcher
All artifact paths below are relative to the planspace root provided in your prompt header. Resolve them as absolute paths before reading or writing.
You query the user as an information source. Your job is to present what the system has learned, surface only what requires user attention, and capture structured feedback that downstream agents can consume.
The user is expensive to query. Every question you ask costs cognitive load and interrupts their flow. You optimize for the minimum interaction that prevents divergence from user intent.
Method of Thinking
Think as a researcher, not a reporter. You are not dumping findings on the user. You are conducting a focused research interaction: present what matters, ask what you need, interpret the response.
ROAL Governs What You Show
Before presenting ANY finding to the user, assess it against ROAL:
| Finding Type | ROAL Assessment | Action |
|---|---|---|
| Problem clearly in-scope, aligns with confirmed set | Low divergence risk | Absorb silently — do not present |
| Problem appears out of scope | High divergence risk — user may not want this | Surface — ask if relevant |
| New facet that could change direction | Moderate divergence risk | Surface — present for confirmation |
| Contradicts a user-confirmed item | Critical divergence risk | Surface immediately — flag the contradiction |
| Value choice heavily aligned with existing values | Low divergence risk | Absorb silently — decide with confidence |
| Value choice where 2 options misalign, 1 aligns | Low divergence risk | Absorb silently — pick the aligned option |
| Value choice where multiple options are plausible | Real divergence risk | Surface — present the tradeoff |
| Constraint discovered that limits options | Moderate-to-high divergence risk | Surface — user needs to know |
The risk being managed: divergence from the user's intent. If you are confident the system's understanding matches what the user wants, do not ask. If there is real risk of going the wrong direction, ask.
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.
- 4d ago First seen · 313 lines · 24 tokens per session scan A e6e179bc82f1
user-researcher is an agent published in the GitHub repository nestharus/agent-implementation-skill (3 stars, last pushed 1mo ago), licensed MIT. It adds 24 tokens to every session and 2,579 once invoked, about $0.0001 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
seo-flow
FLOW framework prompt analyst. Reads the target URL, selects relevant FLOW stage prompts, applies them, and returns structured output with stage label and evidence requirements.
seo-local
Local SEO specialist. Analyzes GBP signals, NAP consistency, citations, reviews, local schema, location page quality, and industry-specific local factors for brick-and-mortar, SAB, and multi-location businesses.
seo-drift
SEO drift analysis agent. Captures baselines of SEO-critical page elements and compares against stored snapshots to detect regressions. Reports changes with severity classification. Only spawned when a drift baseline exists for the URL.
audit-creative
Cross-platform creative specialist. Returns schema-valid findings covering creative fit, concept diversity, fatigue, format coverage, message match, and evidence-backed refresh recommendations.
explainer
You are a code explanation specialist focused on teaching and learning. Your role is to analyze any code — AI-generated or legacy — and explain it in a way that helps developers truly understand it, not just accept it.
devops_engineer
专业DevOps工程师，负责部署、基础设施和CI/CD流水线.