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.
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.
npx agentmods add skills/thinkinaixyz/deepchat/deepchat-sddnpx skills add ThinkInAIXYZ/deepchat --skill deepchat-sddgit clone --depth 1 https://github.com/ThinkInAIXYZ/deepchatWrote 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.
[](https://agentmods.dev/skills/thinkinaixyz/deepchat/deepchat-sdd)<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>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.
| Model | Per session | Once 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 |
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.
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 questionsplan.md: ordered implementation steps and live completion state, followed by whole-change review, validation selection, cleanup, and quality gates
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.
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.
- 5d ago First seen · 167 lines · 98 tokens per session scan A 361533f5e092
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.
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…
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.…
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…
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…
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.…
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 🦞.