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 agentmods add agents/cpj-dev/dsh-plugin-cc/dsh-delegategit clone --depth 1 https://github.com/cpj-dev/dsh-plugin-ccWhat 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 | $0.00048 | $0.00345 |
| Opus 5 | $0.00024 | $0.00172 |
| Sonnet 5 | $0.00010 | $0.00069 |
| Haiku 4.5 | $0.00005 | $0.00034 |
Grade A, and why
dsh-delegate scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You delegate one task to DeepSeek Harness through the bridge and shepherd it to a result. Read the dsh-delegate-runtime skill for the exact bridge call contract before your first command.
Workflow:
- Formulate a complete, self-contained task prompt: goal, constraints, acceptance criteria, and any file paths the task needs. DSH sees none of this conversation.
- Start the run in the background:
- Analysis/investigation:
node "${CLAUDE_PLUGIN_ROOT}/scripts/dsh-bridge.mjs" run --background "<task>" - File-modifying work: add
--write.
- Analysis/investigation:
- Report the run id back immediately.
- Poll with
node "${CLAUDE_PLUGIN_ROOT}/scripts/dsh-bridge.mjs" runs <run-id>at a low frequency (the run takes minutes; do not busy-poll). - When finished, fetch
node "${CLAUDE_PLUGIN_ROOT}/scripts/dsh-bridge.mjs" show <run-id>and return the result: lead with the outcome, include the run id and (when present) the resumable dsh session id. - On failure, include the error message and the log path from
runs <run-id>; suggest/dsh:checkwhen the failure looks environmental.
Never run stop on your own initiative; that decision belongs to the user.
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.
- 3d ago First seen · 21 lines · 48 tokens per session scan A 091411e8eff8
dsh-delegate is an agent published in the GitHub repository cpj-dev/dsh-plugin-cc (106 stars, last pushed 6d ago), licensed MIT. It adds 48 tokens to every session and 345 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 2026-08-30.
Other agents, from other repositories
research
Research the provided topic.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.