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/nexus-substrate/nexus-agents/context-engineeringnpx skills add nexus-substrate/nexus-agents --skill context-engineeringgit clone --depth 1 https://github.com/nexus-substrate/nexus-agentsWrote 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/nexus-substrate/nexus-agents/context-engineering)<a href="https://agentmods.dev/skills/nexus-substrate/nexus-agents/context-engineering"><img src="https://agentmods.dev/badge/skills/nexus-substrate/nexus-agents/context-engineering.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 | $0.00070 | $0.02116 |
| Opus 5 | $0.00035 | $0.01058 |
| Sonnet 5 | $0.00014 | $0.00423 |
| Haiku 4.5 | $0.00007 | $0.00212 |
Grade C, and why
context-engineering scanned grade C with 1 finding 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 3d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- CANONICAL SOURCES: - CLAUDE.md "Context Budget" + "Subagent Context Management" - CLAUDE.md "auto memory" + the persistent memory system at ~/.claude/projects/.../memory/ - .rules/subagent-coordination.md (auto-load How it starts
The opening of the file, as written. The whole thing — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Engineering Skill
When to apply
- Starting a new session — load the right rules + memory + recent state
- Output quality is drifting (wrong patterns, hallucinated APIs, ignoring conventions)
- Fanning out work to subagents — every prompt has a context budget
- Setting up a new project for AI-assisted development
- Switching between unrelated parts of the codebase (start fresh, don't drag old context)
The context hierarchy (most → least persistent)
1. Rules files CLAUDE.md, AGENTS.md, .rules/*.md
2. Memory ~/.claude/projects/.../memory/MEMORY.md + topic files
3. Spec / architecture docs/architecture/*.md, ADRs (loaded per feature)
4. Relevant source source files for the task (loaded per task)
5. Live state error output, test results (loaded per iteration)
6. Conversation accumulates, compacts automatically
Higher levels persist across sessions; lower levels are transient. Engineer the higher levels well — they pay for themselves on every future session.
Level 1 — rules files
Project-wide, always loaded. nexus-agents canonical:
CLAUDE.md— prime directive, type-safety policy, anti-sprawl, autonomous-loop rules, tooling commandsAGENTS.md— per-skill routing keywords for non-Claude tools.rules/*.md— auto-loaded per-topic rules (typescript.md,git.md,subagent-coordination.md,untrusted-input.md, etc.)
Edits here have repo-wide leverage. Treat with care: these are the single biggest input to every future session.
Level 2 — memory
Per-user, cross-session. ~/.claude/projects/-home-william-git-nexus-agents/memory/:
MEMORY.md— index, always loaded. Keep entries to one line < 200 chars.<topic>.md— detail loaded on relevance.- See
CLAUDE.md"auto memory" for what to save (user/feedback/project/reference) and what NOT to save (anything derivable fromgit logor current files).
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.
- 3d ago First seen · 168 lines · 70 tokens per session scan C 5570391f0b5e
context-engineering is a skill published in the GitHub repository nexus-substrate/nexus-agents (18 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 2,116 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
convex-add
Add a capability to the CURRENT Convex app — consults the served Convex capability catalog for always-current procedures (billing, crons, auth, agent, search, …); falls back to built-in hosting or @convex-dev component search. TRIGGER when the user runs /add, or asks to add hosting/publishing or any backend capability…
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
chenhao-limit-up
Use when evaluating A-share limit-up (涨停板) setups through Chen Hao's sentiment and momentum lens: market emotion cycles, board strength, follow-through, and short-term aggressive momentum trading.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
multi-expert-analyzer
针对通用问题进行多领域专家联合分析, 综合稿产生前必经 fact-checker 与 red-team 两道独立校验。适用场景: 用户提出跨领域或不确定领域的复杂问题, 需要从多个专家角度分别搜证并相互校验后综合成文, 例如该不该买房、该不该跳槽、是否进入某个赛道等。触发关键词: 多角度分析、专家分析、综合分析、多视角、跨领域分析、从不同角度看、深度分析。问题只属于单一明确领域时, 优先使用该领域的专门 skill, 例如纯财务用 finance-core-analysis、纯技术用 software-architect。输出 (全部 markdown 保存到当前项目 markdown/ 目录): (1) 每位专家的中间分析稿…