Borrowing it
Nothing to install: this file belongs to shep-ai/shep. 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/shep-ai/shep/main/.claude/skills/shep-kit-research/SKILL.mdgit clone --depth 1 https://github.com/shep-ai/shepWrote 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/shep-ai/shep/shep-kit-research)<a href="https://agentmods.dev/skills/shep-ai/shep/shep-kit-research"><img src="https://agentmods.dev/badge/skills/shep-ai/shep/shep-kit-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/shep-ai/shep/shep-kit-research"><img src="https://agentmods.dev/badge/skills/shep-ai/shep/shep-kit-research.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.01032 |
| Opus 5.5 | $0.00027 | $0.00413 |
| Sonnet 5.5 | $0.00014 | $0.00206 |
| Haiku 4.5 | $0.00007 | $0.00103 |
Grade A, and why
shep-kit: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 1mo 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research Technical Approach
Document technical decisions, library evaluations, and architectural choices for a feature.
Full workflow guide: docs/development/spec-driven-workflow.md
Prerequisites
- Feature spec exists at
specs/NNN-feature-name/spec.yaml(YAML source of truth) - On the feature branch
feat/NNN-feature-name
GATE CHECK (Mandatory)
Before starting research, verify:
- Read
spec.yamland check theopenQuestionsarray - If any unresolved items exist in
openQuestions: STOP and inform user:Cannot proceed with research. Open questions in spec.yaml must be resolved first. Please answer these questions or ensure openQuestions is empty (
openQuestions: []) - Only proceed when the
openQuestionsarray is empty or all items are marked resolved
Workflow
1. Identify Current Feature
Determine which feature we're researching:
- Check current branch name
- Or ask user which spec to research
- Read
specs/NNN-feature-name/spec.yamlfor context
2. Identify Technical Decisions
From the spec, identify decisions that need research:
- Technology/library choices
- Architecture patterns
- Integration approaches
- Performance strategies
3. Research Each Decision
For each technical decision:
Analyze options:
- List 2-4 viable approaches
- Research each using web search, documentation
- Consider project constraints (from
CLAUDE.md, existing patterns)
Evaluate trade-offs:
- Pros and cons of each option
- Compatibility with existing stack
- Learning curve, maintenance burden
- Performance implications
Make recommendation:
- Choose best option with clear rationale
- Document why alternatives were rejected
4. Document Security & Performance
Identify and document:
- Security considerations specific to this feature
- Performance implications and optimizations
5. Write research.yaml and Generate Markdown
Write research output to specs/NNN-feature-name/research.yaml (the source of truth):
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago First seen · 156 lines · 68 tokens per session scan A 908d06f88751
shep-kit:research is a skill published in the GitHub repository shep-ai/shep (267 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 1,032 once invoked, about $0.0003 per session on Opus 5.5. 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
nft-standards
Implement NFT standards (ERC-721, ERC-1155) with proper metadata handling, minting strategies, and marketplace integration. Use when creating NFT contracts, building NFT marketplaces, or implementing digital asset systems.
linkerd-patterns
Implement Linkerd service mesh patterns for lightweight, security-focused service mesh deployments. Use when setting up Linkerd, configuring traffic policies, or implementing zero-trust networking with minimal overhead.
postgresql-table-design
Use this skill when designing or reviewing a PostgreSQL-specific schema. Covers best-practices, data types, indexing, constraints, performance patterns, and advanced features.
spark-training-gotchas
Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.
parallel-feature-development
Coordinate parallel feature development with file ownership strategies, conflict avoidance rules, and integration patterns for multi-agent implementation. Use this skill when decomposing a large feature into independent work streams, when two or more agents need to implement different layers of the same system…
kpi-dashboard-design
Design effective KPI dashboards with metrics selection, visualization best practices, and real-time monitoring patterns. Use this skill when building an executive SaaS metrics dashboard tracking MRR, churn, and LTV/CAC ratios; designing an operations center with live service health and request throughput; creating a…