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 bendrucker/claude --skill prior-artgit clone --depth 1 https://github.com/bendrucker/claudeWrote 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/bendrucker/claude/prior-art)<a href="https://agentmods.dev/skills/bendrucker/claude/prior-art"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/prior-art/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/bendrucker/claude/prior-art"><img src="https://agentmods.dev/badge/skills/bendrucker/claude/prior-art.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 | $0.00043 | $0.00556 |
| Opus 5.5 | $0.00017 | $0.00222 |
| Sonnet 5.5 | $0.00009 | $0.00111 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
research:prior-art 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 2mo 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research prior art for: $ARGUMENTS
Process
Search
Identify relevant sources based on context:
- GitHub: Search for repositories matching the problem space
- Package registries: npm, PyPI, crates.io, pkg.go.dev—infer from current project or query
- Web search: For broader landscape understanding
Run searches in parallel. Infer the ecosystem from:
- Current project's language/framework (if present)
- Query terms (e.g., "React hook for X" implies npm)
- Ask only if genuinely ambiguous
Investigation
Start with 2-3 most promising projects:
- Read README and high-level docs to assess relevance
- Examine code only when relevance is confirmed AND implementation details matter
- Dispatch parallel
Agentcalls per project, with explicit focus areas
If results don't satisfy the query, expand to more projects.
Agent dispatch example:
Investigate [project] for prior art on [topic]:
- How does it approach [specific aspect]?
- What tradeoffs does it make?
- What can we learn for our use case?
Synthesis
Gather findings and produce a recommendation:
- Identify common patterns across solutions
- Note meaningful variations in approach
- Infer intent:
- "build X" → learn patterns, inform implementation
- "library for X" → find dependencies to use directly
Output Format
Respond in the conversation with structured markdown, not files:
## Prior Art: [Topic]
### Summary
[Common patterns, key variations, recommendation based on query intent]
### Projects
#### [Project Name]
- **Repository**: [link]
- **Relevance**: [why this matters to the query]
- **Approach**: [how it solves the problem]
- **Lessons**: [what to learn from it]
#### [Next Project]
...
### Additional Projects (not deeply investigated)
- [Project]: [one-line description]
- ...
Behavior Guidelines
- Honest reporting: Acknowledge when prior art is sparse—don't force results
- Research only: Don't offer to integrate dependencies or modify the project
- Ecosystem inference: Derive from context, don't require explicit specification
- Adaptive depth: Investigate more projects if the initial batch is insufficient
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.
- 2mo ago First seen · 83 lines · 43 tokens per session scan A a38dcd139b6c
research:prior-art is a skill published in the GitHub repository bendrucker/claude (18 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 556 once invoked, about $0.0002 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 2026-09-03.
research:prior-art compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| research:prior-artbendrucker/claude | Skill | 18 | today | MIT | A | 43 | Claude Code |
| reviewSethGammon/Citadel | Skill | 928 | 4d ago | MIT | A | 17 | Claude Code |
| system-upgradealivecontext/alive | Skill | 132 | yesterday | MIT | A | 55 | Claude Code |
| wenlan-handoffwenlan-app/wenlan | Skill | 94 | today | Apache-2.0 | A | 43 | Claude Code, Codex |
| extract-resumesuxrobGM/jobpilot | Skill | 111 | today | MIT | A | 32 | Claude Code |
| pr-reviewnitinjain999/platform-skills | Skill | 71 | yesterday | Apache-2.0 | A | 81 | Claude Code |
| read-literaturefirecrawl/firecrawl-claude-plugin | Skill | 258 | 3d ago | MIT | A | 101 | Claude Code |