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 guyuefangyuanl/deepseek-better-harness --skill harness-session-evidencegit clone --depth 1 https://github.com/guyuefangyuanl/deepseek-better-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/guyuefangyuanl/deepseek-better-harness/harness-session-evidence)<a href="https://agentmods.dev/skills/guyuefangyuanl/deepseek-better-harness/harness-session-evidence"><img src="https://agentmods.dev/badge/skills/guyuefangyuanl/deepseek-better-harness/harness-session-evidence/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/guyuefangyuanl/deepseek-better-harness/harness-session-evidence"><img src="https://agentmods.dev/badge/skills/guyuefangyuanl/deepseek-better-harness/harness-session-evidence.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 | $0.00053 | $0.00201 |
| Opus 5 | $0.00026 | $0.00101 |
| Sonnet 5 | $0.00011 | $0.00040 |
| Haiku 4.5 | $0.00005 | $0.00020 |
Grade A, and why
harness-session-evidence 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 11d 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
Harness Session Evidence
Analyze session behavior without crossing into repository or Agent Asset claims.
- Resolve the authorized session set, time window, task goal, and decision the review must support.
- Prefer bounded facts or task episodes. Read raw transcripts only when the user explicitly authorizes them and no narrower source answers the question.
- Separate observed behavior, missing evidence, and inference.
- Identify repeated friction only from at least two comparable occurrences; one occurrence is a candidate, not a pattern.
- Return evidence candidates without final severity or repository-wide scores.
Read references/session-evidence-contract.md for the candidate schema and rejection rules.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 11d ago First seen · 21 lines · 53 tokens per session scan A 5e31f1e65b57
harness-session-evidence is a skill published in the GitHub repository guyuefangyuanl/deepseek-better-harness (2 stars, last pushed 21d ago), licensed MIT. It adds 53 tokens to every session and 201 once invoked, about $0.0003 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
dsh-web-skin-developer
Build a new skin for the dsh-web skin collection (DSH Web GUI) and publish it into the Skin Center — the first-level settings section — scaffold with scripts/dsh-skin-new, author the v2 skin.json manifest plus skin.css token remap (pure asset directory, no package.json, no build step), validate with scripts/dsh-skin…
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…
yao-ocr
OCR text recognition expert. ALWAYS invoke this skill when you need to extract text from images or PDFs — including invoices, receipts, ID cards, bank cards, business licenses, tables, handwritten documents, or any visual text content.
yao-workspace
Workspace file I/O expert. ALWAYS invoke this skill when you need to list workspaces, read or write files in a workspace on a remote node, or browse workspace directories. Use this for cross-node file operations — for local sandbox files, use standard filesystem tools instead.
figma-code-connect
Creates and maintains Figma Code Connect template files that map Figma components to code snippets. Use when the user mentions Code Connect, Figma component mapping, design-to-code translation, or asks to create/update .figma.ts or .figma.js files.
agentdebug
Use AgentDebugX for trajectory diagnosis only when the user explicitly asks to use AgentDebug, AgentDebugX, or the agentdebug skill. Do not invoke for generic debugging, diagnosis, inspection, or trajectory-review requests.