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 KongFangXun/sofagent --skill fresh-eyes-loopgit clone --depth 1 https://github.com/KongFangXun/sofagentWrote 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/kongfangxun/sofagent/fresh-eyes-loop)<a href="https://agentmods.dev/skills/kongfangxun/sofagent/fresh-eyes-loop"><img src="https://agentmods.dev/badge/skills/kongfangxun/sofagent/fresh-eyes-loop/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/kongfangxun/sofagent/fresh-eyes-loop"><img src="https://agentmods.dev/badge/skills/kongfangxun/sofagent/fresh-eyes-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Rogue Agent · line 49 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 77 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00064 | $0.01735 |
| Opus 5.5 | $0.00026 | $0.00694 |
| Sonnet 5.5 | $0.00013 | $0.00347 |
| Haiku 4.5 | $0.00006 | $0.00173 |
Grade A, and why
fresh-eyes-loop 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 4d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
fresh-eyes-loop · 质量循环定义
一个循环 = 一轮又一轮的"独立审查 → 修复 → 验证"，直到干净为止。
这不是检查清单，是一套让独立性可被重复执行的机制。每一轮都用全新 session 跑（零上下文），所以"作者自己看不出问题"这个人类弱点被结构性消解。
这是什么
一套可复用的质量循环定义。它描述：谁来做（单盲四角色：A 审 / B 修 / C 验 / D 复核）、每一轮怎么走（审查 → 修复 → 验证 → 复核）、什么时候停（连续 2 轮无 P0/P1）、产物放哪（runs/YYYY/MM/DD/run-NN/）。
- A = 审查者（单盲）：独立跑 12 视角审查；发现的质量由下游 C 验收 / D 复核把关（legacy 双盲 B 并行审查走
FORGE_ENABLE_B_CHECK=1逃生门）。 - B/C/D = 工程师执行修复（现行 B 侧为复核模式——独立复核 A 的 P0/P1，可推翻可补充）/ 验收者逐条实测验收（不采信修复自报）/ 复核者对 P0/P1 裁决 CONFIRM / DOWNGRADE / REOPEN。
- 编排者（非 agent）：在角色间中转、维护
runs/文件、判定停止条件。编排者 = 一次 harness session 本身（WorkBuddy 有人值守 / DSH 无头 / Codex headless），注入loop.md「执行形态」节的主任务协议即跑——不存在第二种编排形态（driver 多轮编排循环已随整合归一删除，经验沉淀于FORGE/lessons/driver.md）。
怎么用
- 读
loop.md拿到完整 SOP（角色 / 轮次协议 / 产物 schema / 停止条件）。 - 12 视角的定义见
playbook/fresh-eyes-review.md（A 按它跑）。playbook 共 22 视角六层：1-12 常规发版（driver 循环标准配置）、13-14 文档治理（手动）、15-16 全文档通读（手动/草稿工具）、17-19 动态面（跨组件契约/构建产物/执行证据——需跨包追踪或 build/实跑取证，worker 工具面实测仅sf_read/sf_write/run_bash三件，跨包构建取证超其超时预算，发版审查建议手动追加）、20-21 深度专项（季度全仓体检）、22 发现面（门面改动时）。 loop 与工具的视角边界以 playbook 分层表为准——playbook 演进（如新增视角/调整分层）时，本文件与下游工具同步对齐。 - 四角色的行为指令在
prompts/（a-check / a-consolidate / b-fix / b-audit / c-verify / d-review；b-check 为 legacy 双盲逃生门FORGE_ENABLE_B_CHECK=1时启用）。 - b-audit 步骤：b-fix 改完代码后执行器自动跑
sofagent audit --full --diff——审计每次变更，自用先行铁律。audit FAIL（exit 2）打回 b-fix 重修，不进 c-verify。 - 跨 run 的永久索引在
FORGE/LEDGER.md（被 git 跟踪）；每轮正文在runs/（不进 git）。
实现载体
编排者 = harness session 本身（注入主任务协议即跑，协议 SSOT 见 loop.md「执行形态」节）。角色执行三通道任选：① 编排 session 自身（仅首个角色）② 执行器单步 node FORGE/src/fresh-eyes-driver.mjs --worker --step <step> --round-dir <abs> --target <ver>（DSH 后端；worktree 隔离经 FORGE_WORKTREE_ROOT 环境变量由编排方建立并注入；
内置 stall 守卫、工具软硬熔断、报告质量门控、零发现假绿检测）③ 有头 session 的 subagent。
工具面机制事实（FORGE/lessons/architecture.md）：执行器走 DSH CLI 桥接时，sofagent 自定义工具（sf_read / sf_write / run_bash）在子进程边界不生效——角色实际使用 DSH 自带 bash/fs 工具链，能力等价（读文件/写文件/跑命令）。审查所需证据由 prompt 注入或角色自行 bash 取证。
What ships with it
33 files 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.
- evolution.md 3.6 KB
- loop.md 12 KB
- prompts/a-check-perspective-1.md 3.4 KB
- prompts/a-check-perspective-10.md 3.4 KB
- prompts/a-check-perspective-11.md 3.4 KB
- prompts/a-check-perspective-12.md 3.5 KB
- prompts/a-check-perspective-2.md 3.4 KB
- prompts/a-check-perspective-3.md 3.4 KB
- prompts/a-check-perspective-4.md 3.4 KB
- prompts/a-check-perspective-5.md 3.4 KB
- prompts/a-check-perspective-6.md 3.4 KB
- prompts/a-check-perspective-7.md 3.4 KB
- prompts/a-check-perspective-8.md 3.5 KB
- prompts/a-check-perspective-9.md 3.4 KB
- prompts/a-check.md 3.9 KB
- prompts/a-consolidate.md 6.8 KB
- prompts/a-verify.md 2.4 KB
- prompts/b-check-perspective-1.md 3.5 KB
- prompts/b-check-perspective-10.md 3.5 KB
- prompts/b-check-perspective-11.md 3.4 KB
- prompts/b-check-perspective-12.md 3.5 KB
- prompts/b-check-perspective-2.md 3.4 KB
- prompts/b-check-perspective-3.md 3.4 KB
- prompts/b-check-perspective-4.md 3.4 KB
- prompts/b-check-perspective-5.md 3.4 KB
- prompts/b-check-perspective-6.md 3.5 KB
- prompts/b-check-perspective-7.md 3.4 KB
- prompts/b-check-perspective-8.md 3.5 KB
- prompts/b-check-perspective-9.md 3.4 KB
- prompts/b-check.md 3.5 KB
- prompts/b-fix.md 4.6 KB
- prompts/c-verify.md 2.7 KB
- prompts/d-review.md 3.1 KB
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.
- 4d ago Changed 1ef894ec5f58
- 10d ago Changed ed5711f13719
- 13d ago Changed f9701c782e8a
- 16d ago Changed a05600d6d3ec
- 17d ago Changed eab4ce4acd94
- 21d ago Changed 58ce70bcae26
- 24d ago Changed 131a15a415a0
- 26d ago Changed · +2 lines a574cb3bab5d
- 29d ago Changed · -80 lines f40be54d6ea1
- 1mo ago First seen · 131 lines · 64 tokens per session scan A cac03e773fe3
fresh-eyes-loop is a skill published in the GitHub repository KongFangXun/sofagent (54 stars, last pushed 4d ago), licensed MIT. It adds 64 tokens to every session and 1,735 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
code-review
Perform a structured code review of changes, checking for correctness, style, tests, and potential issues.
adversarial-reviewer
Stress-test a code change for concrete correctness defects, unsafe assumptions, and failure modes. Use when the user explicitly asks for an adversarial review, a deep bug hunt, or to tear a change apart, or to check your own change before submitting it. Do not use for ordinary review, style feedback, or general…
qa-frontend
Internal PostHog developer frontend/browser QA skill. Use only when a PostHog developer explicitly asks to run frontend QA, browser-test a PR, verify a UI flow against the local PostHog stack, use qa-frontend, or QA current frontend changes with browser/runtime evidence, or to make a feature reel (see reel mode…
walkeros-understanding-development
Use when contributing to walkerOS, before writing code, or when unsure about project conventions. Covers build/test/lint workflow, XP principles, folder structure, and package usage.
extending-hobby-smoke-tests
Design, extend, review, or debug PostHog Hobby end-to-end smoke tests in bin/hobby-ci.py and .github/workflows/ci-hobby.yml. Use when adding an ingestion round trip, deciding whether a product belongs in Hobby CI, changing the CI Hobby service topology or API-key scopes, or diagnosing a smoke test that captures data…
hogli
PostHog developer CLI and repo tooling reference. Use when the user mentions hogli, asks about repo CLI tools, bin scripts, Makefiles, how to run/build/test/lint, or any dev environment commands.