Model visibility for DeepSeek Harness: a header chip naming the model and reasoning effort each Session runs on, a subagent dropdown marking which child carries its own route, and sidebar hover cards showing what each conversation did.
Install verification: runtime verified (L5) · tested on dsh 0.2.1-rc.2 · last checked Install verification details →
What it doesAI
Shows which model and reasoning effort each DSH session and subagent runs on via header chips, dropdown badges and hover cards.
- Header chip names the model and reasoning effort per session
- Subagent dropdown marks children with their own model route
- Sidebar hover cards summarize what each conversation did
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 dsh-subagents-modelInstall method: npm · 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
○ The author declares no dsh version requirement — install is not blocked by version.
| plugin ＼ dsh | dsh 0.2.1-rc.2 current | dsh 0.2.1-alpha.4 | dsh 0.2.1-alpha.2 |
|---|---|---|---|
| 1.2.1 | ✓ | ✓ | ✓ |
1.2.1npm✓ 3 runtime-verified2026-10-19
dsh-subagents-model
✓dsh 0.2.1-rc.2current2026-10-19L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.2.1-rc.2
- • Plugin artifact: npm · dsh-subagents-model@1.2.1
ID: dsh-subagents-model@1.2.1@dsh0.2.1-rc.2 · profile: l4-sandbox
Issued: 2026-10-19 · expires: 2026-10-26
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.2.1-alpha.42026-10-16L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.2.1-alpha.4
- • Plugin artifact: npm · dsh-subagents-model@1.2.1
ID: dsh-subagents-model@1.2.1@dsh0.2.1-alpha.4 · profile: l4-sandbox
Issued: 2026-10-16 · expires: 2026-10-23
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✓dsh 0.2.1-alpha.22026-10-15L5 · runtime verified
- • Node.js: v24.14.0
- • DSH: 0.2.1-alpha.2
- • Plugin artifact: npm · dsh-subagents-model@1.2.1
ID: dsh-subagents-model@1.2.1@dsh0.2.1-alpha.2 · profile: l3-fullscan
Issued: 2026-10-15 · expires: 2026-10-22
View checks & evidence
active in loader tree (150 entries)
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
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:
`[](https://www.dsh.so/artifact/dsh-subagents-model/)``[](https://www.dsh.so/artifact/dsh-subagents-model/)`Security Report
Two automated layers, neither a manual review: a static scan (per-plugin rule checks) and a model-driven dynamic security audit that covers only the subset static-flagged at warn or above and never executes plugin code.
Static low, dynamic low — stricter wins → overall low.
v1.2.1dsh manifest1.2.1npm2026-10-211.2.1same versionclean · npmVet is an AST static scan (npm artifact or git source).
show static findings (3)
- criticalnewFunction · code-exec
src/model.js:98new Function('window', source)({ __ModuleLoader__: loader }) - warningnewFunction · code-exec
scripts/install-probe.mjs:95new Function('window', text) - warningnewFunction · code-exec
scripts/unit.mjs:89const invoke = new Function('window', `${source}\nreturn window.__ModuleLoader__`)
show 2 audit findings
- lowBrowser chunk exports are loaded with new Function on a package-local file (test-facing shim)
src/model.js:98Dynamic evaluation exists, but the argument is the text of a fixed package-local file read via readFileSync(new URL('./client.model.js', import.meta.url)), with no attacker-controlled data reaching it; the package main is src/index.js, so this shim is not the Host runtime path and requires an explicit import by a developer or test.
- lowDeveloper install probe invokes npm/tar through a shell with fixed arguments
scripts/install-probe.mjs:54A shell is spawned, but only from the package's own test script, with literal arguments and cwd pinned to the package root; no user or network input is interpolated, so this is a hardening gap rather than a reachable attack surface.
Reviewed surface is a presentation-only client UI plugin; the flagged new Function and shell usage are dev/test-only with no untrusted input, so no exploitable risk was found.
Rule: the dynamic audit can only raise risk, never lower it (raise-only, never an exemption); a wrong raise is withdrawn by human review and the tier falls back to the static verdict. Overall verdict = the stricter of the two layers.
Disclaimer: the static scan and the dynamic security audit are both automated analysis, not a security guarantee. Always review what you install.
Activity
Last commit 2026-10-13 · activity: Active
• Repo created: 2026-10-11
• Stars: ★ 2 · Forks: 0
• Health: Active — committed within last 30 days
Source
Author README
View on GitHub ↗The author's original README from the repository — fetched live, unedited (the English page loads the default README).