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 agentmods add skills/chrislamdev/hermes-core-skills/cross-session-execution-frameworknpx skills add ChrisLamDev/hermes-core-skills --skill cross-session-execution-frameworkgit clone --depth 1 https://github.com/ChrisLamDev/hermes-core-skillsWrote 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/chrislamdev/hermes-core-skills/cross-session-execution-framework)<a href="https://agentmods.dev/skills/chrislamdev/hermes-core-skills/cross-session-execution-framework"><img src="https://agentmods.dev/badge/skills/chrislamdev/hermes-core-skills/cross-session-execution-framework.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.01938 |
| Opus 5 | $0.00009 | $0.00969 |
| Sonnet 5 | $0.00004 | $0.00388 |
| Haiku 4.5 | $0.00002 | $0.00194 |
Grade A, and why
cross-session-execution-framework 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 — 211 lines — stays where its author put it; the contents beside it link to each section on GitHub.
🪷 跨 Session 執行框架
問題
Hermes Agent 每次 Session 有 token/context 限制,跨 Session 開發有以下痛點:
| 問題 | 症狀 |
|---|---|
| Context 遺失 | 新 Session 唔記得上次做咗乜 |
| 任務偏差 | 開始做 A,做到一半改做 B,最後 A 未完成 |
| 進度遺失 | 用戶唔知做到邊一步 |
| 決定遺失 | 之前用戶確認嘅決定,新 Session 要再問一次 |
解決方案:檔案系統實體化
喺 project root 建立 3 個追蹤檔案:
project/
├── ROADMAP.md ← 用戶睇進度
├── STATE.md ← Agent 記錄狀態
└── boot.sh ← 自動行,開工匯報
1. ROADMAP.md — 總路線圖
格式
# 🪷 專案名 — 優化路線圖
> 整體執行進度。✅ = 完成,⬜ = 未開始
## 階段一:XXX
- [x] 1.1 已完成任務(簡短說明)
- [ ] 1.2 未完成任務
## 階段二:XXX
- [ ] 2.1 ...
規則
- 任務用 checkbox 格式
- [ ]/- [x] - 分階段(P0/P1/P2 或 基建/功能/優化)
- 每個 checkbox 對應一個可獨立完成嘅 task
- 唔好放太細粒度(唔好一個 task 就係「改一行 code」)
2. STATE.md — 當前執行狀態
格式
# 🪷 當前執行狀態
## 基本資訊
- **最後更新**:YYYY-MM-DD(Session N)
- **當前階段**:階段一 — ✅ 完成 / 🔄 進行中
- **當前 Task**:XXX
## 已完成
重點 list 已完成嘅 task,每個 task 下面有具體改動 summary
## 已修改/新增檔案
| 檔案 | 狀態 | 說明 |
## 下一個要做
清晰描述下一個 task 係乜
## 待確認事項
1. **問題描述** — 需要用戶決定嘅事
- 選項 A
- 選項 B
## Git 狀態
(如有)
更新規則
- 每次 Session 完結前必須 update
- 「已修改/新增檔案」記錄 exact path,方便下個 Session 快速定位
- 「待確認事項」係最關鍵嘅 section——確保用戶決定唔會 lost
3. boot.sh — 開機腳本
範例
#!/bin/bash
PROJECT_DIR="/path/to/project"
echo "=== 🪷 Boot Sequence ==="
# Check ROADMAP
if [ -f "$PROJECT_DIR/ROADMAP.md" ]; then
echo "✅ ROADMAP.md 存在"
grep -n "\[ \]" "$PROJECT_DIR/ROADMAP.md" | head -10
fi
# Check STATE
if [ -f "$PROJECT_DIR/STATE.md" ]; then
echo "✅ STATE.md 存在"
grep -A 2 "當前階段\|當前 Task\|下一個\|待確認" "$PROJECT_DIR/STATE.md"
fi
# Git status
if [ -d "$PROJECT_DIR/.git" ]; then
git -C "$PROJECT_DIR" status --short
fi
執行時機
- 每次用戶講「開工」時自動執行
- 如果 boot.sh 唔存在,要手動 read_file ROADMAP.md + STATE.md
每次 Session 標準流程
用戶講「開工」
↓
行 boot.sh(或手動檢查 ROADMAP + STATE)
↓
讀 STATE.md → 知道上次進度 + 未確認事項
↓
如果有「待確認事項」→ 先問用戶決定
↓
開始做當前 Task(一個 task 一個 Session)
↓
完成後:
1. 更新 ROADMAP.md(check box)
2. 更新 STATE.md(完成記錄 + 修改檔案 + 下個 task + 新待確認)
↓
匯報完成 + 列出待確認事項
↓
(Session end — 下次重複)
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 First seen · 211 lines · 18 tokens per session scan A 5cbcbd980478
cross-session-execution-framework is a skill published in the GitHub repository ChrisLamDev/hermes-core-skills (9 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 1,938 once invoked, about $0.0001 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
review-sweep
Review oh-my-hermes pull requests that have not been reviewed at their current head commit. Run manually to sweep the open backlog, or pass a number to review one PR. Applies the repository's REVIEW.md policy and posts findings as a GitHub review with inline comments.
triage-sweep
Backfill labels across oh-my-hermes issues and pull requests. Run manually to sweep everything currently unlabeled, or pass a number to triage one item. Use when issues and PRs have accumulated without labels, after adding a new label to .github/labels.yml, or before a release when the backlog needs to be readable by…
team-workflow
Design the team's operating rhythm — task management, collaboration rituals, and tooling. Use when the day-to-day cadence needs structure. For a time-boxed sprint, use design-sprint-plan.
alive:create-walnut
Something new is emerging. A venture, an experiment, a person entering the orbit, a life area getting serious. It needs its own walnut — its own identity, history, and future. Scaffolds the full structure, maps existing context sources, and optionally migrates files across.
implement
End-to-end workflow for taking MCP work items from backlog to merged PR. Handles git branching, schema-driven planning, implementation, independent review, and PR creation. Composes spec-quality, review-quality, and schema-workflow skills into a single pipeline. Use when a user says "implement this", "work on this…
review-proposals
Triages pending improvement-proposal MCP items — presents each with its scope and evidence, collects an accept/reject/defer decision per proposal, and carries out the disposition: project-scoped acceptances get their exact YAML applied to .taskorchestrator/config.yaml and pushed per-root; global acceptances get a…