knowledge-delta-skill-architect

knowledge-delta-skill-architect is a skill for Claude Code, Codex from sergeyizmailov/knowledge-delta-skills. It costs 91 tokens per session (3,326 once invoked), scanned A, original, MIT.

A skill-design tool for writing, reviewing, and shortening instructions that coding agents use for specialised work. It focuses on including information that changes the agent’s behaviour and removing information it already knows.

In plain words
What is it for?
Use it to create a skill for a particular job, improve an existing skill, reduce its size, or decide whether the skill is worth the context it consumes.
Why use it?
It helps keep agent instructions useful without making them unnecessarily long. It also helps identify missing facts, unclear triggers, and rules that may cause the agent to act incorrectly.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions Claude Code.

Good fit Use it to create a skill for a particular job, improve an existing skill, reduce its size, or decide whether the skill is worth the context it consumes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/sergeyizmailov/knowledge-delta-skills/knowledge-delta-skill-architect
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 sergeyizmailov/knowledge-delta-skills --skill knowledge-delta-skill-architect
Clone the repo
git clone --depth 1 https://github.com/sergeyizmailov/knowledge-delta-skills

Made for: Claude Code, Codex.

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 knowledge-delta-skill-architect

README.md
[![agentmods](https://agentmods.dev/badge/skills/sergeyizmailov/knowledge-delta-skills/knowledge-delta-skill-architect/github.svg)](https://agentmods.dev/skills/sergeyizmailov/knowledge-delta-skills/knowledge-delta-skill-architect)
Your own site
<a href="https://agentmods.dev/skills/sergeyizmailov/knowledge-delta-skills/knowledge-delta-skill-architect"><img src="https://agentmods.dev/badge/skills/sergeyizmailov/knowledge-delta-skills/knowledge-delta-skill-architect/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 knowledge-delta-skill-architect

Your own site · 80×15
<a href="https://agentmods.dev/skills/sergeyizmailov/knowledge-delta-skills/knowledge-delta-skill-architect"><img src="https://agentmods.dev/badge/skills/sergeyizmailov/knowledge-delta-skills/knowledge-delta-skill-architect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,326 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.
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 $0.00091 $0.03326
Opus 5 $0.00046 $0.01663
Sonnet 5 $0.00018 $0.00665
Haiku 4.5 $0.00009 $0.00333

Measured 3d ago against content hash 7483e610015a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

knowledge-delta-skill-architect 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 3d 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.

skills/knowledge-delta-skill-architect/SKILL.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Knowledge-Delta Skill Architect

01 02 03 = the numbered files under references/; read triggers in the table at the end. Sources and their limits: 03.

The method here is model- and vendor-independent. What is not — numbers, runtime behavior — is confined to 02: §0 for the numbers, inline flags wherever behavior is runtime-specific. When a spec or a runtime changes, refresh 02.

Spend context only where the model's behavior changes.

Write for the target model, not as a human tutorial. Omit orientation, motivation, definitions, examples and spelled-out reasoning unless the baseline showed they prevent a failure; the gap is sometimes a missing definition. Keep decision rules, conditions, thresholds, discriminators, and the rationale that makes a rule generalize. Your default register is documentation; override it on purpose.

Classes

Class What you saw Content Budget
[W] States it wrong, confidently, and never asks Overwrite the prior Highest value per token
[K] Doesn't know, hedges, or invents plausibly The fact Scale to blast radius
[A] Knows it, skips it under task pressure One imperative line Only if you saw the skip
[O] Solves it acceptably, never considers the stronger option That option + when it wins High — most lore lands here
[R] Gets it right unprompted, and nothing better exists Delete

[R] is a correctness bug, not waste: irrelevant context degrades reasoning, and content topically adjacent to the task degrades it most — telling the model to ignore it barely helps. A redundant paragraph inside your own domain is the most expensive token you can spend [inference]. Numbers: 03.

The path

# Step Detail
1 Scope. Name the concrete tasks this skill must make go right, and the phrasings a user would arrive with. A topic is not a scope below
2 Baseline. Run those tasks with no skill. Record what breaks below
3 Research the confirmed gaps, then one bounded discovery phase below
4 Triage into a keep-list where every rule names what it prevents or unlocks 01
5 Package — hub that routes, references that hold detail; folder name = name field, placed in the runtime's skills directory 02
6 Rerun the build tasks and held-out variants with the draft. Keep only what fixed an observed failure or unlocked a validated capability below
7 Ship check below

Read the full file on GitHub · 226 lines

Files

What ships with it

3 files 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.

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. 3d ago Changed · +19 lines 7483e610015a
  2. 10d ago First seen · 207 lines · 91 tokens per session scan A 8434fea86f7b

Subscribe to this mod's changes

knowledge-delta-skill-architect is a skill published in the GitHub repository sergeyizmailov/knowledge-delta-skills (3 stars, last pushed 3d ago), licensed MIT. It adds 91 tokens to every session and 3,326 once invoked, about $0.0005 per session on Opus 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 2026-08-31.

Related

Other skills, from other repositories

architecture-feature-first

Use when creating a feature, designing folder structure, adding repositories/services/view models, wiring dependency injection, or deciding which layer owns logic.

evanca/flutter-ai-rules · 31 tokens

karpathy-llm-wiki

Use when building or maintaining a personal LLM-powered knowledge base. Triggers: ingesting sources into a wiki, querying wiki knowledge, linting wiki quality, 'add to wiki', 'what do I know about', or any mention of 'LLM wiki' or 'Karpathy wiki'.

Astro-Han/karpathy-llm-wiki · 67 tokens

firebase-ai

Use when setting up firebaseai, generating text/chat with Gemini, streaming AI output, building multimodal prompts, or handling AI errors.

evanca/flutter-ai-rules · 30 tokens

flutter-use-column-row-first

Use when building any Flutter screen or component to choose responsive Row, Column, Expanded, Flexible, and Spacer layouts before fixed-size or coordinate-based alternatives.

evanca/flutter-ai-rules · 36 tokens

deepseek-harness

Use when building AI agent applications with a plugin-based architecture — Web UI, CLI, Python SDK, Cordis plugin system, multi-model orchestration. DeepSeek Harness (dsh): open-source agent harness by DeepSeek AI where everything is a plugin, powered by Cordis for spatiotemporal composability.

znlgis/opengis-skills · 68 tokens

setup

Configure the Qdrant Power after installation. Use this skill for missing uvx, missing environment variables, unapproved environment variables, unavailable Qdrant tools, "Failed to connect" errors, and setup requests.

qdrant/mcp-server-qdrant · 45 tokens