prior-art

prior-art is a skill for Claude Code, Codex from nrdxp/predicate. It costs 66 tokens per session (1,327 once invoked), scanned B, original, MIT.

A procedure for finding and checking existing production code, standards, and research before building a complex algorithm or system.

In plain words
What is it for?
Use it to research design patterns, system protocols, algorithms, library integrations, and peer-reviewed literature, then adapt the findings into your code.
Why use it?
It reduces the risk of inventing an untested approach or relying on one unreliable reference.

Skill for Claude CodeCodex

Part of the predicate plugin — 35 skills shipped together

Install

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.

agentmods
npx agentmods add skills/nrdxp/predicate/prior-art
Any agent
npx skills add nrdxp/predicate --skill prior-art
Clone the repo
git clone --depth 1 https://github.com/nrdxp/predicate

Made for: Claude Code, Codex.

Or install predicate, the plugin that ships this one along with the rest of its 35 skills.

Wrote 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.

agentmods badge for prior-art

README.md
[![agentmods](https://agentmods.dev/badge/skills/nrdxp/predicate/prior-art.svg)](https://agentmods.dev/skills/nrdxp/predicate/prior-art)
Your own site
<a href="https://agentmods.dev/skills/nrdxp/predicate/prior-art"><img src="https://agentmods.dev/badge/skills/nrdxp/predicate/prior-art.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,327 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00066 $0.01327
Opus 5 $0.00033 $0.00664
Sonnet 5 $0.00013 $0.00265
Haiku 4.5 $0.00007 $0.00133

Measured 4d ago against content hash 213cc41e7978, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

prior-art scanned grade B with 1 finding 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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- You **MUST** run `rm -rf .prior_art_cache/` before executing any commit boundary or finalizing a task. No external source code repositories may remain in the active workspace at commit boundaries.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/prior-art/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prior Art & Reference Patterns Skill

Search → Audit → Adapt → Clean

This skill is the procedure the ambient Outward-Search Reflex invokes (ambient.md §"Outward-Search Reflex"). The mandate is ambient — every walker that reaches a design fork, a missing fact, or a non-trivial pattern runs this procedure before halting. The skill documents the how: tiered search, shallow-clone workspace hygiene, ≥2-reference grounding, and cleanup before every commit.

Adversarial path anchor. This lens is also invoked on the Verification Dual's adversarial path (rules.md §2 Invariant 1): the Dual's thesis — externalize correctness, never trust the generator's confidence — applies to external knowledge. Internal confidence is not evidence; a context-free search in decorrelated sources (production code, RFCs, literature) closes the condition where no deterministic evaluator exists.


1. Search Hierarchy Directive

When addressing a non-trivial architectural or algorithmic task, you must systematically search for existing work using the following priority tiers:

graph TD
    A["Start Search Walk"] --> B{"Tier 1: Production Code Available & Permissive?"}
    B -- "Yes" --> C["Audit Code & Extract Invariants (MIT/Apache-2.0)"]
    B -- "No / Restricted (GPL)" --> D{"Tier 2: Official Standards / RFCs Available?"}
    D -- "Yes" --> E["Map Normative Protocol Constraints from Specification"]
    D -- "No" --> F{"Tier 3: Academic Papers / Formal Specifications (arXiv, TLA+)?"}
    F -- "Yes" --> G["Extract Mathematical Theorems & State Transitions"]
    F -- "No" --> H["Halt Sequence: Insufficient Constraints to Warop IBC"]

Tier 1: Production-Grade Code (Permissively Licensed)

  • Search for active open-source projects on GitHub that implement the pattern or algorithm.
  • Look for high maintenance signals: active commits, issues resolved, star density, and test suite coverage.
  • Confirm permissive licensing (e.g., MIT, Apache 2.0, BSD-3-Clause). Do not read copy-restricted code (e.g., GPL, AGPL, proprietary) to avoid licensing contamination.

Read the full file on GitHub · 95 lines

Changes

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.

  1. 4d ago First seen · 95 lines · 66 tokens per session scan B 213cc41e7978

Subscribe to this mod's changes

prior-art is a skill published in the GitHub repository nrdxp/predicate (10 stars, last pushed 3d ago), licensed MIT. It adds 66 tokens to every session and 1,327 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens