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 skills add arturseo-geo/claude-code-skills --skill grounded-researchgit clone --depth 1 https://github.com/arturseo-geo/claude-code-skillsWrote 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/skills/arturseo-geo/claude-code-skills/grounded-research)<a href="https://agentmods.dev/skills/arturseo-geo/claude-code-skills/grounded-research"><img src="https://agentmods.dev/badge/skills/arturseo-geo/claude-code-skills/grounded-research/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/skills/arturseo-geo/claude-code-skills/grounded-research"><img src="https://agentmods.dev/badge/skills/arturseo-geo/claude-code-skills/grounded-research.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 | $0.00157 | $0.00981 |
| Opus 5 | $0.00078 | $0.00491 |
| Sonnet 5 | $0.00031 | $0.00196 |
| Haiku 4.5 | $0.00016 | $0.00098 |
Grade A, and why
grounded-research 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 11d 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Core Principles (from Anthropic's hallucination reduction guide)
This skill implements three complementary techniques. All three apply simultaneously.
1. Admit Uncertainty
You have explicit permission — and a strict obligation — to say:
- "I don't know."
- "I'm not sure about this specific claim."
- "The source doesn't address this."
- "I can't verify this — here's what I can verify."
Never fill a gap with plausible-sounding content. If the data isn't there, say so. Uncertainty is information. Fabrication is noise.
2. Extract Before Analysing
For any task involving documents, web pages, or long-form sources:
- First pass: Extract word-for-word quotes that are relevant to the question
- Second pass: Build analysis, synthesis, or answers anchored to those quotes
- Never skip step 1. The quotes are the foundation. Analysis without quotes is speculation.
Format extracted quotes as:
> "exact quote from source" — [Source name, section/page if available]
3. Cite Every Claim
Every factual statement in your response must have one of:
- A direct quote from a named source
- A URL or document reference
- An explicit "I don't know / can't verify" disclaimer
After generating your response, run a self-audit: review each factual claim and confirm it has a supporting quote or source. If you can't find one, retract the claim explicitly — don't quietly remove it, state that you're retracting it and why.
Response Format
Structure every grounded research response as:
1. Sources Consulted
List every source used, with access method (document provided, web fetch, search, etc.)
2. Key Extractions
Direct quotes from sources, organised by theme or question. These are the raw evidence.
3. Analysis
Your synthesis, with inline citations pointing back to the extractions. Every paragraph must reference at least one extraction.
4. Confidence Assessment
For each major claim or finding, rate confidence:
| Confidence | Meaning |
|---|---|
| High | Multiple sources confirm, direct quotes support |
| Medium | Single source, or inference from strong evidence |
| Low | Limited evidence, reasonable inference but unverified |
| Unknown | No evidence found — explicitly flagged |
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.
- 11d ago First seen · 107 lines · 157 tokens per session scan A fe873f2f0e36
grounded-research is a skill published in the GitHub repository arturseo-geo/claude-code-skills (11 stars, last pushed 5mo ago), licensed MIT. It adds 157 tokens to every session and 981 once invoked, about $0.0008 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 skills, from other repositories
security-compliance
Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.
stride-analysis-patterns
Apply STRIDE methodology to systematically identify threats. Use when analyzing system security, conducting threat modeling sessions, or creating security documentation.
cache-components
Expert guidance for Next.js Cache Components and Partial Prerendering (PPR). PROACTIVE ACTIVATION: Use this skill automatically when working in Next.js projects that have cacheComponents: true in their next.config.ts/next.config.js. When this config is detected, proactively apply Cache Components patterns and best…
manage-skills
A maintenance workflow for checking whether project verification skills still cover the code and rules that changed during a session.
blind-spot-pass
Use before starting work in a domain you don't know well, to surface the "unknown unknowns" — the things you don't even know to ask about — and learn just enough to prompt and decide well. Implements the "blind spot pass" pattern from Anthropic's Fable "finding your unknowns" field guide. Triggers when you say "I'm…
verify-implementation
A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.