Borrowing it
Nothing to install: this file belongs to AsiaOstrich/EngramGraph. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AsiaOstrich/EngramGraph/main/.agents/skills/durable-execution-assistant/SKILL.mdgit clone --depth 1 https://github.com/AsiaOstrich/EngramGraphWrote 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/asiaostrich/engramgraph/durable-execution-assistant)<a href="https://agentmods.dev/skills/asiaostrich/engramgraph/durable-execution-assistant"><img src="https://agentmods.dev/badge/skills/asiaostrich/engramgraph/durable-execution-assistant/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/asiaostrich/engramgraph/durable-execution-assistant"><img src="https://agentmods.dev/badge/skills/asiaostrich/engramgraph/durable-execution-assistant.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 | $0.00108 | $0.01363 |
| Opus 5.5 | $0.00043 | $0.00545 |
| Sonnet 5.5 | $0.00022 | $0.00273 |
| Haiku 4.5 | $0.00011 | $0.00136 |
Grade A, and why
durable 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 14d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Durable Execution Assistant | 持久執行助手
Guide fault-tolerant workflow design with automatic recovery, checkpoints, and retry strategies.
引導容錯工作流程設計，包含自動恢復、檢查點與重試策略。
Usage | 使用方式
| Command | Purpose | 用途 |
|---|---|---|
/durable |
Start interactive failure recovery guide | 啟動互動式故障恢復引導 |
/durable --checkpoint |
Design checkpoint strategy | 設計檢查點策略 |
/durable --retry |
Configure retry policies | 配置重試策略 |
/durable --rollback |
Plan rollback procedures | 規劃回滾程序 |
/durable <workflow> |
Analyze specific workflow for durability | 分析特定工作流的持久性 |
Core Concepts | 核心概念
| Concept | Definition | 定義 |
|---|---|---|
| Checkpoint | Save execution state at known-good points | 在已知正確的位置儲存執行狀態 |
| Retry | Automatically re-attempt failed operations | 自動重新嘗試失敗的操作 |
| Rollback | Revert to last known-good state on failure | 失敗時回復到上一個已知正確狀態 |
| Idempotency | Operations produce same result on re-execution | 操作重新執行時產生相同結果 |
| Circuit Breaker | Stop retries when failure rate exceeds threshold | 失敗率超過閾值時停止重試 |
Failure Recovery Decision Tree | 故障恢復決策樹
Failure detected
├── Is it transient? (network, timeout)
│ ├── Yes → Retry with backoff
│ └── No → Is state corrupted?
│ ├── Yes → Rollback to checkpoint
│ └── No → Is it a logic error?
│ ├── Yes → Stop, report, fix code
│ └── No → Escalate with diagnostics
Retry Strategy Guide | 重試策略指南
| Strategy | When to Use | Config | 使用時機 |
|---|---|---|---|
| Immediate | Rare glitches, fast ops | max 2 retries | 罕見故障、快速操作 |
| Exponential Backoff | Network/API calls | base 1s, max 30s | 網路/API 呼叫 |
| Circuit Breaker | Downstream service issues | threshold 50%, window 60s | 下游服務問題 |
| Dead Letter | Unrecoverable after retries | max 5 retries then queue | 重試後仍不可恢復 |
Checkpoint Granularity | 檢查點粒度
| Granularity | Use Case | 使用場景 |
|---|---|---|
| Per-step | Long pipelines (> 5 steps) | 長管線（> 5 步驟） |
| Per-batch | Bulk data processing | 批量資料處理 |
| Per-phase | Multi-phase workflows | 多階段工作流程 |
| Start/End | Short, atomic operations | 短暫的原子操作 |
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.
- 14d ago First seen · 121 lines · 108 tokens per session scan A 6298fe55e6b5
durable is a skill published in the GitHub repository AsiaOstrich/EngramGraph (3 stars, last pushed today), licensed MIT. It adds 108 tokens to every session and 1,363 once invoked, about $0.0004 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 2026-10-16.
Other skills, from other repositories
kivgraph
Use Kivgraph's local MCP server to search symbols, read their source, and follow references, dependencies, cross-repository consumers and graph status in the indexed code graph.
mushroom
Live graph memory for agents — query and create entities, derive relationships by rule, explain why two things are associated, read the graph at a past commit, ask what a change would do, and answer as one role. Trigger on: memory, remember, recall, relationship, entity, association, why are X and Y related, as of…
omnigraph
Operate OmniGraph graphs and deployments. Use for .pg schemas, .gq queries, OmniGraph CLI commands, file:///s3:///az:// graph URIs, cluster.yaml, operator config, bearer-authenticated servers, graph-backed knowledge or memory, Blob values, embeddings, branches, commits, and change feeds. Apply especially before schema…
code-graph
This skill should be used when understanding code structure, finding dependencies between functions/classes, tracing call graphs, or exploring code relationships. Trigger phrases include 'code graph', 'call graph', 'who calls', 'what calls', 'find dependencies', 'code structure', 'inheritance', 'find paths'.
usage
Query LeanKG knowledge graph for code understanding. Use when exploring a codebase, finding functions, tracing dependencies, or calculating impact radius.
codestory-grounding
Use when discovering repository structure, tracing relationships, analyzing change impact, or validating CodeStory retrieval or an installed plugin through the CodeStory plugin MCP. Skip only for bounded inspection or editing of named files that does not require those operations.