signal-dense

signal-dense is a skill for Claude Code from bartolli/kmd. It costs 96 tokens per session (2,549 once invoked), scanned C, original, MIT.

A response style for conversations where assistant messages are reused as context in later turns. It uses consistent names for concepts and adjusts its register for technical, emotional, safety, or beginner-focused messages.

In plain words
What is it for?
It is for applying canonical terms, typed entities, and direct statements to chat responses, code comments, and docstrings when its trigger conditions are met.
Why use it?
It makes important information easier for an agent to track across turns by reducing vague wording and unnecessary self-commentary.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the wiki-sdd plugin — 10 skills, 5 hooks shipped together

Good fit It is for applying canonical terms, typed entities, and direct statements to chat responses, code comments, and docstrings when its trigger conditions are met.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/bartolli/kmd/signal-dense
View source ↗ bartolli/kmd
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 bartolli/kmd --skill signal-dense
Clone the repo
git clone --depth 1 https://github.com/bartolli/kmd

Made for: Claude Code.

Or install wiki-sdd, the plugin that ships this one along with the rest of its 10 skills, 5 hooks.

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 signal-dense

README.md
[![agentmods](https://agentmods.dev/badge/skills/bartolli/kmd/signal-dense/github.svg)](https://agentmods.dev/skills/bartolli/kmd/signal-dense)
Your own site
<a href="https://agentmods.dev/skills/bartolli/kmd/signal-dense"><img src="https://agentmods.dev/badge/skills/bartolli/kmd/signal-dense/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 signal-dense

Your own site · 80×15
<a href="https://agentmods.dev/skills/bartolli/kmd/signal-dense"><img src="https://agentmods.dev/badge/skills/bartolli/kmd/signal-dense.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,549 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00096 $0.02549
Opus 5 $0.00048 $0.01274
Sonnet 5 $0.00019 $0.00510
Haiku 4.5 $0.00010 $0.00255

Measured 2d ago against content hash f14b20a2bbbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade C, and why

signal-dense scanned grade C 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 2d 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 deletehighDestructive command

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

| `safety_critical` | irreversible verb or intent (`drop`, `delete`, `force-push`, `rm -rf`, `truncate`, `revoke`) targeting production or shared state | suspend compression on the consequence statement; use § Safety-bri
plugins/claude/wiki-sdd/skills/signal-dense/SKILL.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Respond declaratively in canonical vocabulary. Preserve grammar. Remove self-narration. Optimize attention-window signal density across the thread, not raw brevity.

Scope

Chat responses; code comments and docstrings via § Code documentation guard.

Excluded: README, tutorials, onboarding artifacts written for first-time readers; tool input parameters where exact phrasing affects routing or matching. For excluded surfaces, the artifact's audience controls register.

Activation

Active until explicit "stop signal-dense" or "normal mode". Active means § Register predicates evaluate every turn; transformations apply only when at least one predicate fires.

Register predicates

Each turn evaluates four predicates independently. Predicates compose. When all four are false, the skill applies no transformations.

Predicate Signals Effect
technical_present identifiers, error strings, type signatures, code fences, version numbers, stack traces, CLI flags, protocol literals, architecture/design terms, ownership/boundary decisions apply § Hard rules + § Judgment rules
affect_present first-person affect, distress/frustration, venting, interpersonal stakes open with one acknowledgment sentence in plain English; then apply rules iff technical_present
safety_critical irreversible verb or intent (drop, delete, force-push, rm -rf, truncate, revoke) targeting production or shared state suspend compression on the consequence statement; use § Safety-bridge form
beginner_cue definition request; explicit beginner self-id; unfamiliar-use signal, including questions about canonical handles define-then-bind on the unfamiliar handle, then continue dense

Affect acknowledgment names the burden or stake in one sentence. No reassurance boilerplate, praise, or therapy-script language.

Hard rules

  • Preserve grammar: articles, copulas, conjunctions.
  • Preserve scope words: not, only, all, every, unless, except, iff.
  • Quote exact technical strings verbatim: identifiers, error messages, version numbers, regex, API names, CLI flags, file paths, query strings.
  • Type entities on first mention: entity (type/role).
  • Use only the fixed abbreviation lexicon: DB, auth, config, req/res, fn, impl, repo, ctx, env, MCP, LLM, KG, BPE, RDF, JWT, API, IO. No invented abbreviations.
  • No invented arrows beyond § Notation.
  • Established terms (see § Project-term binding) are referential units; do not re-expand.

Read the full file on GitHub · 188 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. 2d ago Changed f14b20a2bbbe
  2. 3d ago Changed 42a03edda8ba
  3. 4d ago Changed 7583b23e4358
  4. 9d ago First seen · 188 lines · 96 tokens per session scan C 378761d36ae5

Subscribe to this mod's changes

signal-dense is a skill published in the GitHub repository bartolli/kmd (7 stars, last pushed 3d ago), licensed MIT. It adds 96 tokens to every session and 2,549 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C 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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens