deepchat-sdd

deepchat-sdd is a skill for Claude Code, Codex from ThinkInAIXYZ/deepchat. It costs 98 tokens per session (1,786 once invoked), scanned A, original, Apache-2.0.

A planning guide for substantial changes to the DeepChat project. It creates a durable written decision record and a clear path for carrying out the work.

In plain words
What is it for?
Use it before major features, architecture changes, migrations, complex bugs, or changes to DeepChat’s code, tests, documentation, configuration, or build process.
Why use it?
It prevents large changes from starting without shared context or agreed decisions. It also helps distinguish work that needs planning from small fixes that do not.

Skill for Claude CodeCodex

About the project

DeepChat is an open-source desktop client for AI agents that keeps user data local first and connects agents with services such as MCP, Skills, ACP, and messaging apps. It is for people who want to use and control AI assistants from a desktop application. The catalogue add-ons extend DeepChat’s agent workflows.

ThinkInAIXYZ/deepchat · 6,304 stars · on GitHub

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/thinkinaixyz/deepchat/deepchat-sdd
Any agent
npx skills add ThinkInAIXYZ/deepchat --skill deepchat-sdd
Clone the repo
git clone --depth 1 https://github.com/ThinkInAIXYZ/deepchat

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 deepchat-sdd

README.md
[![agentmods](https://agentmods.dev/badge/skills/thinkinaixyz/deepchat/deepchat-sdd.svg)](https://agentmods.dev/skills/thinkinaixyz/deepchat/deepchat-sdd)
Your own site
<a href="https://agentmods.dev/skills/thinkinaixyz/deepchat/deepchat-sdd"><img src="https://agentmods.dev/badge/skills/thinkinaixyz/deepchat/deepchat-sdd.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,786 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00098 $0.01786
Opus 5 $0.00049 $0.00893
Sonnet 5 $0.00020 $0.00357
Haiku 4.5 $0.00010 $0.00179

Measured 5d ago against content hash 361533f5e092, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deepchat-sdd 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 5d 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.

.agents/skills/deepchat-sdd/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DeepChat SDD

When To Use

Use this skill before substantial DeepChat source code, configuration, tests, docs, build scripts, release workflows, or project structure changes that need shared context or a durable decision record.

Skip SDD for trivial or tightly localized work unless the developer explicitly asks for it:

  • visual/style fixes, copy changes, and small UI layout adjustments
  • simple localized logic changes with a clear owner module
  • routine docs edits that do not change project direction
  • release metadata already covered by the release flow

If the scope is unclear, inspect first and then ask whether SDD is wanted instead of creating artifacts by default.

Classify The Goal

Create one kebab-case folder per goal:

  • New capability, user-visible behavior, integration, or tool large enough to need a shared plan: docs/features/<goal>/
  • Complex bug, regression, failing test, CI failure, reliability problem, or prompt/runtime issue: docs/issues/<goal>/
  • Refactor, migration, dependency boundary, shared contract, runtime architecture, or cross-module design: docs/architecture/<goal>/

If one request contains multiple independent goals, split them into separate folders. Keep current architecture reference docs such as docs/architecture/agent-system.md in place; use subfolders for new architecture targets.

Treat a bug as SDD-worthy only when the root cause, blast radius, or fix path is complex enough that future developers benefit from the written record. For simple style defects or obvious local logic fixes, skip docs/issues/* and implement directly.

If a bug fix introduces a new user-visible capability, data migration, public contract, or cross-module redesign, classify the work as feature or architecture instead.

Required Artifacts

Feature and architecture goals use two artifacts:

  • spec.md: the normative RFC covering context, goals, non-goals, design, ownership, interfaces, data flow, invariants, compatibility, acceptance criteria, and open questions
  • plan.md: ordered implementation steps and live completion state, followed by whole-change review, validation selection, cleanup, and quality gates

Read the full file on GitHub · 167 lines

Files

What ships with it

1 file 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. 5d ago First seen · 167 lines · 98 tokens per session scan A 361533f5e092

Subscribe to this mod's changes

deepchat-sdd is a skill published in the GitHub repository ThinkInAIXYZ/deepchat (6,304 stars, last pushed yesterday), licensed Apache-2.0. It adds 98 tokens to every session and 1,786 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 2026-08-30.

Related

Other skills, from other repositories

audit-i18n

Audit localization / i18n coverage across the compose-resources surface (9 modules x 9 locales). Finds strings that exist in English but not in some or all languages, keys left as untranslated English stubs inside a translated file, stale keys the base dropped, and English literals that never reached a strings.xml at…

garfiec/Librechat-Mobile · 120 tokens

sync-upstream

Sync the Switchboard client with a newer official LibreChat server version — a stable release, a release candidate, or a PARTIAL sync up to an untagged upstream commit (e.g. current dev HEAD). If the client is ALREADY at the target commit, runs an AUDIT of the last synced delta to catch anything that was missed.…

garfiec/Librechat-Mobile · 89 tokens

audit-deps

Audit open dependabot PRs in this repo. Spawns one investigator per PR (each with a codebase-walk sub-agent), produces a comparison table with per-PR risk + recommendation, and proposes a merge order that minimizes rebase churn. Audit-only — stops at recommendations; user authorizes execution. Use when dependabot has…

garfiec/Librechat-Mobile · 86 tokens

release-highlights

Add a hand-written Highlights section to a GitHub release whose notes were auto-generated, summarizing the release's PRs in user-facing language above the generated changelog. Reads every PR in the range, drafts the section in the repo's house style, asks about ambiguous wording, and writes only after approval. Use…

garfiec/Librechat-Mobile · 94 tokens

update-web-assets

Update the third-party JavaScript vendored into the app for the artifact, diagram, and math WebViews (KaTeX, mermaid, marked, highlight.js, Tailwind, Babel, React). Checks what is outdated, reads each pin's rationale before proposing a bump, re-downloads from the official source, verifies the lock, and runs the gates.…

garfiec/Librechat-Mobile · 124 tokens

proactive-agent

Transform AI agents from task-followers into proactive partners that anticipate needs and continuously improve. Now with WAL Protocol, Working Buffer, Autonomous Crons, and battle-tested patterns. Part of the Hal Stack 🦞.

MerkyorLynn/Lynn · 46 tokens