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 FuRongJun-1999/dsh-memory --skill compiler-4cbbda95git clone --depth 1 https://github.com/FuRongJun-1999/dsh-memoryWrote 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/furongjun-1999/dsh-memory/compiler-4cbbda95)<a href="https://agentmods.dev/skills/furongjun-1999/dsh-memory/compiler-4cbbda95"><img src="https://agentmods.dev/badge/skills/furongjun-1999/dsh-memory/compiler-4cbbda95/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/furongjun-1999/dsh-memory/compiler-4cbbda95"><img src="https://agentmods.dev/badge/skills/furongjun-1999/dsh-memory/compiler-4cbbda95.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 | $0.00079 | $0.00397 |
| Opus 5.5 | $0.00032 | $0.00159 |
| Sonnet 5.5 | $0.00016 | $0.00079 |
| Haiku 4.5 | $0.00008 | $0.00040 |
Grade A, and why
compiler-4cbbda95 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 1mo 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
编译-指令（compiler-4cbbda95）
When to use
任务「编译指令」；对照：INSTRUCTION_MAP（道→create_path 等；未接入指令诚实边界）。
克制条款（不适用条件）
kind 非 {DAO, DE} 时
How to execute
按 op 分派；顺序调用
Verification
- 单元样例 4 条（cases 断言）
- 物理基底：按 calibration 对照（编译/运行/断言裁决）
References
- 单元库：compiler_code_units.py「编译-指令」
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.
- 1mo ago First seen · 46 lines · 79 tokens per session scan A 18f3c1cea090
compiler-4cbbda95 is a skill published in the GitHub repository FuRongJun-1999/dsh-memory (536 stars, last pushed yesterday), licensed MIT. It adds 79 tokens to every session and 397 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 2026-09-11.
Other skills, from other repositories
strata-memory
Installs and operates strata-memory, an open-source MCP memory server that stores vetted facts in local SQLite and recalls them as short cards before expanding full text. Use when the user asks for persistent agent memory, long-term context across sessions, shared memory for multiple agents, or help connecting an MCP…
graphify
Use for any question about a codebase, its architecture, file relationships, or project content — especially when graphify-out/ exists, where the question should be treated as a graphify query first. Turns any input (code, docs, papers, images, videos) into a persistent knowledge graph with god nodes, community…
potpie-source-ingestion
Use when the user explicitly asks to ingest, refresh, or deeply understand a repository, PR, issue, ticket, runbook, incident report, document, or web link into Potpie. The harness performs todo-driven discovery, uses local/GitHub/integration tools and read-only subagents when available, builds evidence-backed…
potpie-resource-markdown
Use when the user asks to ingest a markdown or HTML document — an exported doc, wiki or Confluence page, web page, runbook, spec, or RFC — into Potpie so agents can search and cite it. Teaches the extraction-script flow: split on the heading tree into sections and 4k-char chunks, import with potpie resource import…
potpie-repo-baseline
Use when establishing, refreshing, or deeply understanding a repository's baseline memory in Potpie: purpose, application type, features, services/modules, environments, deploy shape, dependencies, API contracts, datastores, integrations, ownership, and explicit preferences. The harness reads authored and…
potpie-project-preferences
Use before writing, modifying, reviewing, refactoring, or testing code so repo/project preferences surface: error handling, file structure, frameworks, logging, dependency choices, testing, security, API style, and naming. Also use after code work when a reusable project preference should be recorded.