agentmods.dev

nw-density-resolution-contract

nw-density-resolution-contract is a skill for Claude Code from nWave-ai/nWave. It costs 65 tokens per session (2,393 once invoked), scanned A, original, MIT.

A shared rule set for choosing how much documentation a workflow should show at each stage. It defines always-visible references, optional explanations, detail levels, a resolver for selecting them, and documentation telemetry.

In plain words
What is it for?
Use it when building or maintaining multi-stage agent workflows that emit feature documentation with consistent detail levels and machine-readable tracking.
Why use it?
It prevents every workflow from repeating the same documentation rules and helps keep basic output concise while retaining deeper explanations when needed. The input does not describe a separate product feature beyond this documentation contract.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

not rated 620repo +4 1mo ago A scan SkillSpector: warn 65 tokens original MIT

Good fit Use it when building or maintaining multi-stage agent workflows that emit feature documentation with consistent detail levels and machine-readable tracking.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nwave-ai/nwave/nw-density-resolution-contract
View source ↗ nWave-ai/nWave nwave.ai
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.

Any agent
npx skills add nWave-ai/nWave --skill nw-density-resolution-contract
Clone the repo
git clone --depth 1 https://github.com/nWave-ai/nWave

Made for: Claude Code.

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 nw-density-resolution-contract

README.md
[![agentmods](https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-density-resolution-contract/github.svg)](https://agentmods.dev/skills/nwave-ai/nwave/nw-density-resolution-contract)
Your own site
<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-density-resolution-contract"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-density-resolution-contract/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.

agentmods 80×15 button for nw-density-resolution-contract

Your own site · 80×15
<a href="https://agentmods.dev/skills/nwave-ai/nwave/nw-density-resolution-contract"><img src="https://agentmods.dev/badge/skills/nwave-ai/nwave/nw-density-resolution-contract.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,393 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Agent Snooping · line 37
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Rogue Agent · line 85
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
How audits are shown
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 5.1 $0.00065 $0.02393
Opus 5.5 $0.00026 $0.00957
Sonnet 5.5 $0.00013 $0.00479
Haiku 4.5 $0.00006 $0.00239

Measured 1mo ago against content hash 7c6ba9b8a8a4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nw-density-resolution-contract 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.

nWave/skills/nw-density-resolution-contract/SKILL.md · 107 lines

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.

Density Resolution Contract (shared across wave skills)

This skill is the canonical source for the density-aware behaviour every wave skill must implement. Wave skills inherit it by reference and keep a brief inline summary so phrase-grep contract tests stay green; full detail lives here so the same boilerplate is not duplicated six times.

Provenance: feature lean-wave-documentation — D2 (schema-typed sections), D4 (telemetry instrumented day-one), D6 (first-install pedagogical prompt), D10 (one-line expansion descriptions), D12 (rigor cascade), DDD-5 (density resolver shared utility), DDD-6 (telemetry event lives in DES domain).

Output Tiers (per D2 + D10)

Each wave emits a single feature-delta.md whose headings are typed [REF] (always emitted) or [WHY]/[HOW] (lazy expansions). Tier-1 is the always-on baseline; Tier-2 is the lazily-rendered expansion catalog. The .feature file (DISTILL) and other machine artifacts remain the SSOT for executable content; the wave-delta sections are pointers + structured summaries.

  • Tier-1 [REF] — emitted under ## Wave: <NAME> / [REF] <Section> headings on every run. Wave-specific list of [REF] sections lives in each wave skill.
  • Tier-2 EXPANSION CATALOG — NOT emitted by default. Rendered only when explicitly requested via --expand <id> (DDD-2), via the broad wave-end menu when expansion_prompt = "ask", or via a trigger-scoped menu when expansion_prompt = "ask-intelligent" and the active wave declares a matching trigger. Each item has a one-line description (per D10) so the menu fits in a single render. Each emitted Tier-2 section is headed ## Wave: <NAME> / [WHY] <Section> or ## Wave: <NAME> / [HOW] <Section>. The catalog itself is wave-specific.

Density resolution (per D12)

Before emitting any Tier-1 section, resolve the active documentation density:

  1. Read ~/.nwave/global-config.json. Treat missing/malformed config as empty dict (fall back to defaults).
  2. Call resolve_density(global_config) from scripts/shared/density_config.py. The function returns a Density value object with fields mode ("lean" | "full"), expansion_prompt ("ask" | "ask-intelligent" | "always-skip" | "always-expand" | "smart"), and provenance (the cascade branch that produced this result).
  3. Branch on density.mode:
    • lean → emit ONLY Tier-1 [REF] sections. Do NOT auto-render Tier-2 items.
    • full → emit Tier-1 [REF] sections PLUS all Tier-2 expansion items rendered under their [WHY] / [HOW] headings. This is auto-expansion (no menu).
  4. At wave end, branch on density.expansion_prompt:
    • "ask" → present the expansion menu (Tier-2 catalog with one-line descriptions per D10) and append user-selected items as ## Wave: <NAME> / [WHY|HOW] <Section> headings.
    • "ask-intelligent" → use only triggers explicitly declared by the active wave and present only the matching Tier-2 items. If the wave has no declared triggers, or none fires, present no menu; never infer or invent a trigger.
    • "always-skip" → no menu, no extra sections (idempotent re-runs, CI mode).
    • "always-expand" → equivalent to mode = "full" for this run; auto-render every Tier-2 item.
    • "smart" → out of scope for v1 (per OQ-3); treat as "ask" until heuristic is empirically tuned.

Read the full file on GitHub · 107 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. 1mo ago First seen · 107 lines · 65 tokens per session scan A 7c6ba9b8a8a4

Subscribe to this mod's changes

nw-density-resolution-contract is a skill published in the GitHub repository nWave-ai/nWave (620 stars, last pushed 1mo ago), licensed MIT. It adds 65 tokens to every session and 2,393 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 2026-09-03.

Building agentsClaude CodeDevOps and cloudTDDWriting and docsagentic-aiaisoftware-architecture
Related

Other skills, from other repositories

engineering-workflow

A Chinese-language workflow for reliable software development. It describes exploring the problem, making a plan, using TDD (test-driven development, where tests are written before the code), debugging methodically, reviewing code, and verifying the result.

TencentCloud/Octop · 47 tokens

tdd

Use only when the user explicitly asks for TDD, a failing test, or a regression test, OR when the bug has an obvious cheap local test target. Skip when the test path is unclear, expensive, integration-heavy, or not requested.

michael-denyer/pstack-claude · 52 tokens

moai-run

Implement SPEC requirements using DDD/TDD methodology.

modu-ai/moai-adk · 13 tokens

test-driven-development

Strict RED-GREEN-REFACTOR cycle enforcement. Tests are never skipped or deferred. Run mode only, never watch mode. Exit code evidence mandatory.

a5c-ai/babysitter · 35 tokens

tdd-enforcement

Red-Green-Refactor TDD methodology with mandatory failing tests, minimal implementation, quality refactoring, and 80% coverage gating.

a5c-ai/babysitter · 33 tokens

story-development

Implement user stories with test-driven development methodology.

a5c-ai/babysitter · 0 tokens