agentmods.dev

harness-session-evidence

harness-session-evidence is a skill for Claude Code, Codex from guyuefangyuanl/deepseek-better-harness. It costs 53 tokens per session (201 once invoked), scanned A, original, MIT.

A guide for reviewing approved records of sessions in which a developer worked with an agent.

In plain words
What is it for?
Use it to review authorised session facts, compare repeated work episodes, and produce evidence candidates for a review.
Why use it?
It helps identify repeated obstacles, missing feedback, and evidence about results without treating private reasoning or a whole repository as evidence.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 1repo 2mo ago A scan 53 tokens original MIT

Good fit Use it to review authorised session facts, compare repeated work episodes, and produce evidence candidates for a review.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/guyuefangyuanl/deepseek-better-harness/harness-session-evidence
View source ↗ guyuefangyuanl/deepseek-better-harness
Install

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.

Any agent
npx skills add guyuefangyuanl/deepseek-better-harness --skill harness-session-evidence
Clone the repo
git clone --depth 1 https://github.com/guyuefangyuanl/deepseek-better-harness

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for harness-session-evidence

README.md
[![agentmods](https://agentmods.dev/badge/skills/guyuefangyuanl/deepseek-better-harness/harness-session-evidence/github.svg)](https://agentmods.dev/skills/guyuefangyuanl/deepseek-better-harness/harness-session-evidence)
Your own site
<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.

agentmods 80×15 button for harness-session-evidence

Your own site · 80×15
<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>
Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 201 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00053 $0.00201
Opus 5.5 $0.00021 $0.00080
Sonnet 5.5 $0.00011 $0.00040
Haiku 4.5 $0.00005 $0.00020

Measured 2mo ago against content hash 5e31f1e65b57, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

packages/session-evidence/skills/harness-session-evidence/SKILL.md · 21 lines

What it actually says

Harness Session Evidence

Analyze session behavior without crossing into repository or Agent Asset claims.

  1. Resolve the authorized session set, time window, task goal, and decision the review must support.
  2. Prefer bounded facts or task episodes. Read raw transcripts only when the user explicitly authorizes them and no narrower source answers the question.
  3. Separate observed behavior, missing evidence, and inference.
  4. Identify repeated friction only from at least two comparable occurrences; one occurrence is a candidate, not a pattern.
  5. Return evidence candidates without final severity or repository-wide scores.

Read references/session-evidence-contract.md for the candidate schema and rejection rules.

Files

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.

Changes

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.

  1. 2mo ago First seen · 21 lines · 53 tokens per session scan A 5e31f1e65b57

Subscribe to this mod's changes

harness-session-evidence is a skill published in the GitHub repository guyuefangyuanl/deepseek-better-harness (1 stars, last pushed 2mo ago), licensed MIT. It adds 53 tokens to every session and 201 once invoked, about $0.0002 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 2026-08-31.

Building agentsagent-skillsai-agentbetter-harnessdeepseek-harnessdsh-pluginqoder
Related

harness-session-evidence compared with skills from other repositories

harness-session-evidence next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
harness-session-evidenceguyuefangyuanl/deepseek-better-harnessSkill12mo agoMITA53Claude Code, Codex
feynman-perspectivealchaincyf/nuwa-skillSkill38kyesterdayMITA212Claude Code, Codex
naval-perspectivealchaincyf/nuwa-skillSkill38kyesterdayMITA218Claude Code, Codex
x-mastery-mentoralchaincyf/nuwa-skillSkill38kyesterdayMITA197Claude Code, Codex
elon-musk-perspectivealchaincyf/nuwa-skillSkill38kyesterdayMITA228Claude Code, Codex
ilya-sutskever-perspectivealchaincyf/nuwa-skillSkill38kyesterdayMITA183Claude Code, Codex
dsh-tui-guideccch1mneyyy/dsh-TUISkill7.4ktodayMITA41Claude Code, Codex