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 Dong90/oh-my-taiyiforge --skill taiyi-compressgit clone --depth 1 https://github.com/Dong90/oh-my-taiyiforgeWrote 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/dong90/oh-my-taiyiforge/taiyi-compress)<a href="https://agentmods.dev/skills/dong90/oh-my-taiyiforge/taiyi-compress"><img src="https://agentmods.dev/badge/skills/dong90/oh-my-taiyiforge/taiyi-compress/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/dong90/oh-my-taiyiforge/taiyi-compress"><img src="https://agentmods.dev/badge/skills/dong90/oh-my-taiyiforge/taiyi-compress.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00051 | $0.00813 |
| Opus 5 | $0.00026 | $0.00407 |
| Sonnet 5 | $0.00010 | $0.00163 |
| Haiku 4.5 | $0.00005 | $0.00081 |
Grade A, and why
taiyi-compress 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 13d 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
taiyi-compress
目的
在 Token 接近预算或工件过大时，分层压缩上下文：先用引擎零 LLM 截断，再按需加载第三方 Skill 隔离/落盘会话。
何时使用
| 信号 | 动作 |
|---|---|
/taiyi:status 出现 Token ⚠ 或压缩建议 |
读本 Skill |
工件 scan > compressThreshold（默认 120k） |
先 /taiyi:token compress |
| dev / 多 slice 并行 | Superpowers subagent / parallel |
| 长会话 / 换窗口 / compaction 前 | /taiyi:handoff 或 ECC strategic-compact |
策略（与 Superpowers 双线 harness 同级）
1. 引擎（首选 · 零 LLM Token）
用户说 /taiyi:token compress <slug>；Agent 代跑：
scripts/taiyi-forge.sh token compress <slug>
产出 .taiyi/changes/<slug>/CONTEXT-COMPACT.md。后续阶段优先读此文件，再按需打开单工件。
2. Superpowers（聊天 Skill · optional）
| Skill | 用途 |
|---|---|
subagent-driven-development |
大实现拆 subagent，主会话只协调（省主窗 token） |
dispatching-parallel-agents |
多 slice 并行，各 agent 不继承主会话历史 |
打卡（auto 模式 optional）：
scripts/taiyi-forge.sh harness-check <slug> superpowers/subagent-driven-development
3. ECC / handoff（聊天 Skill · optional）
| 方式 | 用途 |
|---|---|
ecc/strategic-compact |
战略级会话压缩 |
/taiyi:handoff |
写 HANDOFF.md，新会话续作 |
scripts/taiyi-forge.sh harness-check <slug> ecc/strategic-compact
推荐顺序
/taiyi:token scan <slug>— 了解工件体量/taiyi:token compress <slug>— 引擎摘要- 若仍超预算 / 进入 dev：加载 subagent-driven-development
- 会话结束前：/taiyi:handoff 或 ecc/strategic-compact
/taiyi:token record <slug> <n> --phase <phase> --label "compress-flow"
配置
反模式
- 在已超阈值时仍全量读 CHANGE…CHANGELOG 进聊天
- 跳过 CONTEXT-COMPACT 重复 grep 全库
- 主会话直接实现多个 TASK slice（应 subagent）
- completed 变更不 archive、探针 slug 堆在 workspace（污染
/taiyi:list与对话上下文） - 在聊天里跑全量 E2E / npm test / probe（日志灌上下文；应 CI 后台 + TEST.md 摘要）
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.
- 13d ago First seen · 77 lines · 51 tokens per session scan A 1032548c465b
taiyi-compress is a skill published in the GitHub repository Dong90/oh-my-taiyiforge (888 stars, last pushed 5d ago), licensed MIT. It adds 51 tokens to every session and 813 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 2026-08-30.
Other skills, from other repositories
codebase-memory-mcp
Resolve canonical Git checkouts, index and verify codebase-memory-mcp graphs through the guarded CLI, and safely audit duplicate worktree caches. Use when a user mentions codebase memory MCP, searchgraph, tracepath, indexrepository, worktree indexes, or oversized graph caches.
unified-memory
Share durable, inspectable context and handoffs between Claude, Codex, Hermes, Cursor, OpenCode, and other agents through the local ECC Memory Vault. Use when an agent must save work state, transfer context, resume another agent's task, or search shared project knowledge.
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.
notes
Skill "notes" from Pinvou/pinvou-agent, covering ima notes, operations, write rules, examples and response handling.
review
Use when the user wants code assessed rather than changed — "review PR 88", "is this branch ready to merge?", "look over my changes", "any problems with this diff?", "give me a code review", "what do you think of this PR?", "sanity-check this branch", "ship it?". Applies to a pull request or the current branch when…
fix
PRFlow's code-review reception skill (formerly receiving-code-review), used by the review-and-fix loop and available directly. Use when addressing review feedback already posted on a pull request — verifying findings before applying them — as distinct from /prflow:review-and-fix, which runs the review itself and then…