DeepSeek Harness is an open-source framework for building and running AI agents, organized so that its functionality is provided through plugins. Developers use it to launch agent workflows through a local web interface or from source, while the catalogue add-ons extend the harness as plugins.
Borrowing it
Nothing to install: this file belongs to deepseek-ai/deepseek-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/deepseek-ai/deepseek-harness/master/.agents/skills/dsh-error-handling/SKILL.mdgit clone --depth 1 https://github.com/deepseek-ai/deepseek-harnessWrote 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/deepseek-ai/deepseek-harness/dsh-error-handling)<a href="https://agentmods.dev/skills/deepseek-ai/deepseek-harness/dsh-error-handling"><img src="https://agentmods.dev/badge/skills/deepseek-ai/deepseek-harness/dsh-error-handling/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/deepseek-ai/deepseek-harness/dsh-error-handling"><img src="https://agentmods.dev/badge/skills/deepseek-ai/deepseek-harness/dsh-error-handling.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 | $0.00030 | $0.00440 |
| Opus 5.5 | $0.00012 | $0.00176 |
| Sonnet 5.5 | $0.00006 | $0.00088 |
| Haiku 4.5 | $0.00003 | $0.00044 |
Grade A, and why
dsh-error-handling 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 6d 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 — 31 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeepSeek Harness Error Handling
Define failures, their owners, and what remains safe after failure.
Typed, structured failures
Expected failures need declared types, stable discriminants, and handling-relevant details. Reuse package error conventions, preserve causes, and separate machine identity from display text. Never route handling by parsing messages. Unexpected defects such as assertNever may remain plain Error; containment must never turn them into success.
Catch, recover, or stop
For each failure, define handling and reporting owners, containment, and guarantees in the owning API documentation: valid invariants, absent/partial/committed/unknown effects, and cleanup responsibility. Background work retains these obligations.
Catching limits exception propagation, not mutations. Only the affected state's owner can establish safe continuation. Otherwise stop dependent work, discard invalid state or instances, or escalate. Logging alone is not recovery. Retries require safe repetition, cancellation, and an explicit owner; finite operations need budgets, while continuing supervision needs lifecycle ownership and observable degradation.
Localized, actionable, visible reports
Every final report needs a readable summary, affected operation, and safe next action. Localize through the receiving application's locale mechanism where one exists; other diagnostics use their existing output language. Keep sensitive internal details out of user-facing text.
Untrusted state or unknown outcomes must be visible through UI or default-enabled, accessible logs: report the impact, uncertainty, system disposition, and safe next step. Persistent invalid state needs persistent visibility. Never claim success, rollback, or safe retry without guarantees. Reporting failures need an independent fallback.
Verify resulting state and visible outcomes, not merely that an exception was caught.
Foundations
Meyer's Object-Oriented Software Construction (1997): contracts and invariants; Sutter's Exceptional C++ (1999): exception safety guarantees; Armstrong's thesis (2003): isolation and supervision.
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.
- 6d ago First seen · 31 lines · 30 tokens per session scan A fcde7e278056
dsh-error-handling is a skill published in the GitHub repository deepseek-ai/deepseek-harness (250,433 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 440 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-10.
Other skills, from other repositories
diagnosing-bugs
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
manage-taskboard
Manage work in the native DeepSeek Harness Taskboard with exact task ids and optimistic versions. Use when an Agent must inspect project work, claim an eligible todo, record progress or blockers, verify an implementation, submit it for human review, or release its own claim; also use when a human asks how to accept…
industry-research-method
A Chinese-language method for researching an industry by mapping its supply chain, tracking policies and news, and writing sourced reports. It separates the chain into upstream inputs, midstream production, and downstream distribution or use.
company-research-method
A documented process for researching a company using supplied files and selected public sources. It produces a company overview with business details, sourced financial figures, and stated risks.
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.