Automatic strong/cheap model-tier routing for DeepSeek Harness: intent-gated tier landing on the agent/request waterfall, plan-mode handoff (strong plans, cheap implements), deterministic high-risk guards on tools/pre-execute, failure escalation with TTL fallback, a /tier command, and tier status tools
Install verification: sandbox install ok, web smoke failed (L5) · tested on dsh 0.2.1-rc.2 · last checked Install verification details →
What it doesAI
Routes DeepSeek Harness requests to strong or cheap model tiers with intent gating, plan handoff, risk guards, and failure escalation.
- Intent-gated tier landing on the agent/request waterfall
- Plan-mode handoff: strong models plan, cheap models implement
- Failure escalation with TTL fallback, /tier command and status tools
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-autotier@0.2.19security scan passed · npm package v0.2.19
Install method: npm · sandbox install ok, web smoke failed (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
Based on 1 requirement(s) across 15 @deepseek-ai/dsh-* packages. raw ranges
>=0.1.6-0 <0.2.0 || >=0.2.0-0 <0.3.0 || >=0.2.1-0 <0.3.0 ×15
✓ Running dsh 0.2.1-rc.2 is within the declared range — install is not blocked by version.
Footnote: the author also wrote engines.dsh = ">=0.1.6-0 <0.2.0 || >=0.2.0-0 <0.3.0 || >=0.2.1-0 <0.3.0" — DSH does not read that field (not part of the verdict).
Whether it actually runs is a separate question → see the measured matrix below (L1–L5).
| plugin ＼ dsh | dsh 0.2.1-rc.2 current | dsh 0.2.1-alpha.4 | dsh 0.2.1-alpha.2 | dsh 0.2.0-rc.2 | dsh 0.2.0-rc.1 |
|---|---|---|---|---|---|
| 0.2.19 | ✗ | ✗ | · | · | · |
| 0.2.16 | · | · | ✗ | · | · |
| 0.2.15 | · | · | · | ✗ | · |
| 0.2.8 | · | · | · | · | ✗ |
| 0.2.7 | · | · | · | · | · |
0.2.19npm2 failed2026-10-21
dsh-autotier
✗dsh 0.2.1-rc.2current2026-10-21L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.2.1-rc.2
- • Plugin artifact: npm · dsh-autotier@0.2.19
ID: dsh-autotier@0.2.19@dsh0.2.1-rc.2 · profile: l3-fullscan
Issued: 2026-10-21 · expires: 2026-10-28
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✗dsh 0.2.1-alpha.42026-10-18L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.2.1-alpha.4
- • Plugin artifact: npm · dsh-autotier@0.2.19
ID: dsh-autotier@0.2.19@dsh0.2.1-alpha.4 · profile: l5-web-smoke
Issued: 2026-10-18 · expires: 2027-01-16
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
0.2.16npm1 failed2026-10-18
dsh-autotier
✗dsh 0.2.1-alpha.22026-10-13L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.2.1-alpha.2
- • Plugin artifact: npm · dsh-autotier@0.2.16
ID: dsh-autotier@0.2.16@dsh0.2.1-alpha.2 · profile: l3-fullscan
Issued: 2026-10-13 · expires: 2026-10-20
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
0.2.15npm1 failed2026-10-10
dsh-autotier
✗dsh 0.2.0-rc.22026-10-09L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.2.0-rc.2
- • Plugin artifact: npm · dsh-autotier@0.2.15
ID: dsh-autotier@0.2.15@dsh0.2.0-rc.2 · profile: l4-sandbox
Issued: 2026-10-09 · expires: 2026-10-16
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
0.2.8npm2 failed2026-10-04
dsh-autotier
✗dsh 0.2.0-rc.12026-09-30L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.2.0-rc.1
- • Plugin artifact: npm · dsh-autotier@0.2.8
ID: dsh-autotier@0.2.8@dsh0.2.0-rc.1 · profile: l4-sandbox
Issued: 2026-09-30 · expires: 2026-10-07
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
✗prehistory2026-10-04L5 · failed
- • Node.js: v24.14.0
- • DSH: unknown
- • Plugin artifact: npm · dsh-autotier@0.2.8
ID: dsh-autotier@0.2.8@dshunknown · profile: l4-sandbox
Issued: 2026-10-04 · expires: 2026-10-11
View checks & evidence
L1–L3 are plugin-level static conclusions (baseline, identical across dsh versions): evidence is stored once per plugin.
0.2.7npm1 failed2026-09-25
dsh-autotier
✗dsh 0.1.7-rc.22026-09-25L5 · failed
- • Node.js: v24.14.0
- • DSH: 0.1.7-rc.2
- • Plugin artifact: npm · dsh-autotier@0.2.7
ID: dsh-autotier@0.2.7@dsh0.1.7-rc.2 · profile: l4-sandbox
Issued: 2026-09-25 · expires: 2026-10-02
View checks & evidence
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-autotier/)``[](https://www.dsh.so/artifact/dsh-autotier/)`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 no conclusion (static stands) → overall low.
v0.2.19dsh manifest0.2.19npm2026-10-240.2.19same versionclean · npmVet is an AST static scan (npm artifact or git source).
not in the dynamic queue (the queue only covers plugins whose static tier is medium or above — medium/high/critical; since 2026-10-24 entries rated low are not audited even when dsh-only rules logged warnings) — this does not mean the dynamic audit found it safe.
Rule (2026-10-24): when a dynamic conclusion exists it is authoritative (it may raise or lower the level); without one, the static/vet fused tier applies. The audit never writes the exemption list (exemptions are manual only); a wrong conclusion is withdrawn by human review and the tier falls back to static/vet.
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 2026-10-23 · activity: Active
• Repo created: 2026-09-09
• Stars: ★ 1 · 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).