dsh-optimize

Long-session resource control for DeepSeek Harness: measures the context every request carries, warns at configurable thresholds, can run the harness compaction engine over budget, and contains offscreen chat rows behind a toggle.

PluginAI ModelsNetworkStorageMemoryNotifications

Verification

L5 · Run tested

Passed

Risk

Low

Health

Active

Trust

Gold

Install verification: runtime verified (L5) · tested on dsh 0.1.5-rc.2 · last checked 09-14Install verification details →

What it doesAI

Measures per-request context size in long DeepSeek Harness sessions, warns at thresholds, compacts over budget, and hides offscreen chat rows.

Measures the context every request carries
Configurable warnings when budget thresholds are exceeded
Runs the harness compaction engine and hides offscreen chat rows

aiAImemoryAInotificationAI

Capability tags are AI-inferred or rule-extracted from the README (see badge) — vocabulary-limited, not install-verified. AI = inferred; README = literal keyword from the readme.

Installation

dsh plugin --profile web add github:aoripus/dsh-optimize

security scan passed · default branch source

Install method: GitHub · runtime verified (L5)

Verification & Compatibility

Grouped by plugin version: each card lists the dsh versions actually tested against that artifact version and their install verdicts (L5 wins). Untested combinations are omitted — absence means untested, never assumed compatible. L1–L3 are a plugin-level static archive (independent of the dsh version — the same verdict on every dsh row): they sit in each row's level grid next to L4/L5, marked "static", while their evidence is stored once per plugin inside that row's "checks & evidence" instead of being duplicated per version.

External credentials (plugin-level): none detected

Install compatibility (by plugin version, dsh versions within)

Legend:✓ L5 runtime verified◐ L4 testing · install passed○ ecosystem app✗ failed

No runtime install test (L4/L5) yet.

Only the latest 3 published versions are shown; source-snapshot (commit hash) groups, unstated groups and older versions are omitted — the full archive stays in the data layer (snapshot/unstated groups appear only when a plugin has no published version).

Author badges

Embed the official badges in your README to showcase security & install-test status:

Security Report

Automated static scan, not manual review.

DSH.SO VETPASSED525903

Security reviewAutomated review · daily

PASSED

Vet static analysis found no suspicious behavior — verdict is clean.

0 critical·0 high·0 medium

Version binding

plugin versionv0.1.0dsh manifest

scanned version0.1.0git2026-09-14

current version07e4eb1921f8version moved on

vet verdictclean · git

Vet is an AST static scan (npm artifact or git source).

Disclaimer: automated static analysis, not a security guarantee. Always review what you install.

Risk details

No critical or warning findings.

Activity

Last commit 2026-09-14 · activity: Active

• Repo created: 2026-09-14

• Stars: ★ 0 · Forks: 0

• Health: Active — committed within last 30 days

Source

GitHub: github.com/aoripus/dsh-optimize

Plugin notes

What is the dsh-optimize DeepSeek Harness plugin?

dsh-optimize is a DeepSeek Harness plugin maintained by @aoripus. It is cataloged on dsh.so as a AI Models plugin for Memory tasks, with a public GitHub source, declared install command, and automated static security scan.

How do I install dsh-optimize?

Run dsh plugin --profile web add github:aoripus/dsh-optimize in a DeepSeek Harness (dsh) environment. This exact command has been verified by a real install inside an isolated windows-acl sandbox (L4) plus web smoke testing (L5).

How does the security scan relate to a manual audit?

The scan is automated static analysis of the repository source — a scalable first line of defense that can produce false positives and miss context; it is not a manual security audit. Before using a plugin, review the repository and installed permissions, and combine the scan with the verification level (L4/L5) and health signals.

"DeepSeek Harness (dsh) is an open-source agent harness developed by DeepSeek AI. It uses an architecture where everything is a plugin, and is powered by Cordis."
— DeepSeek Harness README

Sources: GitHub repository · DeepSeek Harness README · security scan data · Maintained by dsh.so · Last updated 2026-09-14