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 skills add SparkElf/deepseek-harness-plus --skill dsh-speed-up-perfgit clone --depth 1 https://github.com/SparkElf/deepseek-harness-plusWrote 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/sparkelf/deepseek-harness-plus/dsh-speed-up-perf)<a href="https://agentmods.dev/skills/sparkelf/deepseek-harness-plus/dsh-speed-up-perf"><img src="https://agentmods.dev/badge/skills/sparkelf/deepseek-harness-plus/dsh-speed-up-perf/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sparkelf/deepseek-harness-plus/dsh-speed-up-perf"><img src="https://agentmods.dev/badge/skills/sparkelf/deepseek-harness-plus/dsh-speed-up-perf.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00045 | $0.02196 |
| Opus 5.5 | $0.00018 | $0.00878 |
| Sonnet 5.5 | $0.00009 | $0.00439 |
| Haiku 4.5 | $0.00005 | $0.00220 |
Grade A, and why
dsh-speed-up-perf 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 1mo 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.
This is a copy
100% identical to dsh-speed-up-perf — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Speed Up DeepSeek Harness
Turn a broad “make it faster” request into reproducible user-path measurements and small, evidence-backed fixes. This is guidance, not a quota or a script: survey broadly, follow measured cost, and reject attractive changes that do not improve the workload users actually run.
Establish scope and current authority
Read AGENTS.md, architecture, testing policy, defensive patterns, and the affected packages’ instructions and Agent Notes. Use CI test reliability for processes, clocks, browser tests, and asynchronous cleanup.
Agree on the user-visible endpoint, workload range, resource constraints, acceptable minor behavior differences, and stopping rule. Keep backend and browser end-to-end measurements separate: a fast history iterator or Client fold does not prove fast transport, paint, scrolling, or input response. Exclude model/network latency when measuring local overhead, and state that exclusion rather than calling the result complete product latency.
Inspect the exact current base, not just the running checkout. Study final merged diffs, owning source, tests, and resolved review threads; a PR body can describe an abandoned implementation. Separate merged, closed-unmerged, superseded, estimated, and newly measured evidence. The performance workflow decision and evidence supply historical leads, not authority to reintroduce their implementations.
Survey user paths, then rank candidates
Delegate independent domains when breadth helps; require measurements and production call sites, not guesses. Useful domains include:
- Cold profile startup, first historical read, current-generation reopen, and writable resume.
- Many-turn and tool-heavy history, large individual messages/results, child Session listing, and repeated navigation among Sessions.
- Initial history transport and fold, first usable browser paint, older-page loading, scrolling, tool expansion, and inactive-view activation.
- Live streaming and reconnect, including a long active attempt, interleaved tool work, settlement, cancellation, and teardown.
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.
- 1mo ago First seen · 93 lines · 45 tokens per session scan A f71345f9e7b3
dsh-speed-up-perf is a skill published in the GitHub repository SparkElf/deepseek-harness-plus (1 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 2,196 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 100% identical to dsh-speed-up-perf, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Diagnose failures from runtime evidence before editing code.
dsh-tui-guide
Use when the user asks about dsh-tui itself (usage, shortcuts, config, themes, migration, VS Code). Load before answering; skip for normal coding tasks.
dsh-troubleshoot
A troubleshooting guide for DeepSeek Harness, including its process, configuration, plugins, tools, skills, and model connections.
ask-good-questions
Guidance for asking technical questions and reporting bugs so another developer can reproduce and answer them. It covers versions, environment details, minimal reproduction steps, expected and actual results, errors, and attempted fixes.
error-handling
A set of rules for deciding how software should report failures and what information error messages should contain.
platform-diagnostics
A read-only diagnostic procedure for checking whether an OpenQuantum platform's user interface, task runner, skills, and models are connected correctly. It produces a report with evidence for each check.