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 yidapan666-creator/dsh-gate --skill dsh-supervised-workergit clone --depth 1 https://github.com/yidapan666-creator/dsh-gateWrote 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/yidapan666-creator/dsh-gate/dsh-supervised-worker)<a href="https://agentmods.dev/skills/yidapan666-creator/dsh-gate/dsh-supervised-worker"><img src="https://agentmods.dev/badge/skills/yidapan666-creator/dsh-gate/dsh-supervised-worker/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/yidapan666-creator/dsh-gate/dsh-supervised-worker"><img src="https://agentmods.dev/badge/skills/yidapan666-creator/dsh-gate/dsh-supervised-worker.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 | $0.00049 | $0.00395 |
| Opus 5 | $0.00024 | $0.00198 |
| Sonnet 5 | $0.00010 | $0.00079 |
| Haiku 4.5 | $0.00005 | $0.00040 |
Grade A, and why
dsh-supervised-worker 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 8d 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.
What it actually says
DSH Supervised Worker
Read the task packet's taskId, completionToken, objective, and writer mode before acting.
- Work only inside the session cwd. In
read_onlymode, do not mutate the working tree. - Before adding infrastructure or an abstraction, search the repository and installed dependencies for a reusable implementation.
- When a recovery attempt fails, call
supervisor_report_failurewith a stable, worker-chosen semanticfailureSignatureand the attempted hypothesis. The runtime limits the budget for that reported signature; it does not infer semantic similarity for you. - Verify changes with the narrowest relevant tests, then typecheck, lint, or build in proportion to risk.
- Report artifacts as relative paths inside the session cwd. Absolute paths, traversal, symlinks, hardlinks, non-files, and paths resolving outside the cwd are rejected. Keep
supervisor_handoff.summaryat or below 2048 characters; when more detail is needed, write a Markdown report under.dsh-handoff/<taskId>/inside the session cwd (gitignored), include its relative path inartifacts, and reference it from the concise summary. - End with exactly one
supervisor_handoff. Include the matchingtaskIdandcompletionToken, status, concise summary, files, verification, blockers or failure data, and artifacts. The successful tool call concludes the turn.
Use completed only when the objective and verification are complete. Use blocked, major_checkpoint, escalation_required, or failed accurately. A plain final message or turn end is never a successful handoff.
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.
- 8d ago First seen · 18 lines · 49 tokens per session scan A cc429e1a401a
dsh-supervised-worker is a skill published in the GitHub repository yidapan666-creator/dsh-gate (0 stars, last pushed 17d ago), licensed MIT. It adds 49 tokens to every session and 395 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
shortfilm-prompt
A five-part method for writing prompts for AI-generated videos, such as Sora or Seedance. It organizes each prompt into the subject, setting, visual style, camera movement, and timed shots with sound.
skill
Ten native DSH tools give a text-only agent eyes. Use these structured tools directly; do not shell out to the bundled Python scripts or reproduce their implementation. Vision API credentials and model settings are managed by the plugin, so tool calls do not receive credentials.
modsearch
Plug-in web search, X (Twitter) search, and page fetch for models without native web access. Use whenever the task needs current information, external facts, source links, posts from X, or the content of a specific URL, and the active model/harness has no native search or fetch tool. Runs the modsearch CLI to return…
submit-dsh-plugin
A submission checklist and workflow for adding a DeepSeek Harness plugin to the community’s public catalogue. It prepares the catalogue entry and checks the plugin’s repository, metadata, tests, and required files.
ticket-triage
Triage and prioritize a support ticket or customer issue. Use when a new ticket comes in and needs categorization, assigning P1-P4 priority, deciding which team should handle it, or checking whether it's a duplicate or known issue before routing.
variance-analysis
Decompose financial variances into drivers with narrative explanations and waterfall analysis. Use when analyzing budget vs. actual, period-over-period changes, revenue or expense variances, or preparing variance commentary for leadership.