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 kanghelyu/dsh-deepseek-flow --skill deepseek-flowgit clone --depth 1 https://github.com/kanghelyu/dsh-deepseek-flowWrote 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/kanghelyu/dsh-deepseek-flow/deepseek-flow)<a href="https://agentmods.dev/skills/kanghelyu/dsh-deepseek-flow/deepseek-flow"><img src="https://agentmods.dev/badge/skills/kanghelyu/dsh-deepseek-flow/deepseek-flow/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/kanghelyu/dsh-deepseek-flow/deepseek-flow"><img src="https://agentmods.dev/badge/skills/kanghelyu/dsh-deepseek-flow/deepseek-flow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 10 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00027 | $0.01880 |
| Opus 5 | $0.00014 | $0.00940 |
| Sonnet 5 | $0.00005 | $0.00376 |
| Haiku 4.5 | $0.00003 | $0.00188 |
Grade A, and why
deepseek-flow 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeepSeek Flow
Use this skill whenever the user wants to build, import, visualize, or modify a multi-step workflow. Once the request is clear, call the tool directly; do not ask the user to confirm details again.
Creating and updating
- Prefer
flow_createfor new workflows. It createsWORKFLOW.md, oneSTEP.mdworkspace per step, and the canvas nodes and edges. - To update an existing workflow, first call
flow_readto get the currentrevision, then callflow_putwith thatexpected_revision. - A successful
flow_createorflow_putalready persists the topology. Do not ask the user to click "Apply changes" in Studio, and do not send the same topology back to the main Session for review. Studio syncs byrevisionautomatically. - If you edit an existing workflow's
WORKFLOW.md,STEP.md, or definition files directly (without usingflow_put) and the edit changes nodes, gates, or arrows, callflow_finalize_canvasafter the file changes, passing the workflowid(and preferably theexpected_revisionfromflow_read). It triggers an invisible deterministic finalize in Studio and saves directly without another main-Session review. - Even if you forget
flow_finalize_canvas, Studio falls back to detecting that no canvas edit event occurred and presses the same hidden finalize path automatically. Canvas drafts created by the user in Studio still require "Apply changes". - Ordinary execution edges must be acyclic. For bounded retries, add an explicit feedback edge:
{"source":"review","target":"implement","feedback":{"maxIterations":3,"exitCondition":"quality check passed"}}. Feedback edges must have an integer limit between 1 and 1000 and a non-emptyexitCondition. They do not participate in single-pass Boolean gate evaluation and do not auto-run Agent steps; the current Session must control each retry according toWORKFLOW.md.
Naming language
- Use concise workflow names in the user's language. If the user did not specify a name,
flow_creategenerates a default name in the language you pass. - Pass
language: "en"orlanguage: "zh"toflow_createso default node labels (Input,Output,Step N) and the default four steps match the user's language. If omitted, the default is Chinese for backward compatibility; you should set it to the language the user is currently using.
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.
- 10d ago First seen · 102 lines · 27 tokens per session scan A 79759a7460e6
deepseek-flow is a skill published in the GitHub repository kanghelyu/dsh-deepseek-flow (69 stars, last pushed 21d ago), licensed MIT. It adds 27 tokens to every session and 1,880 once invoked, about $0.0001 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 skills, from other repositories
ospec
Document-driven OSpec workflow for initialization, change/goal routing, validation, archiving, and durable project knowledge.
ospec-change
Create or advance a lightweight OSpec change using the classic fast workflow.
browser-remote-control
Use when an AI agent needs to automate a real browser through Agent Browser Bridge CLI, including remote Chrome control, page extraction, clicking, typing, navigation, or screenshots.
prismflow-draft-revision
Read stable PrismFlow Drafts, revise an unapproved Draft, or derive an image-bound revision from an approved Draft, with exact version and SHA-256 concurrency checks.
prismflow-memory-read
A retrieval tool for finding relevant entries in PrismFlow’s long-term memory and knowledge base. PrismFlow is the system where those saved project details and past decisions are stored.
prismflow-memory-write
A memory-management instruction set for PrismFlowAgent. The available description mentions saving memory and a required memory format, but does not explain the broader behavior.