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/swimmwatch/cloakbrowser-mcp/context-engineeringnpx skills add swimmwatch/cloakbrowser-mcp --skill context-engineeringgit clone --depth 1 https://github.com/swimmwatch/cloakbrowser-mcpWrote 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/swimmwatch/cloakbrowser-mcp/context-engineering)<a href="https://agentmods.dev/skills/swimmwatch/cloakbrowser-mcp/context-engineering"><img src="https://agentmods.dev/badge/skills/swimmwatch/cloakbrowser-mcp/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 | $0.00082 | $0.00389 |
| Opus 5 | $0.00041 | $0.00195 |
| Sonnet 5 | $0.00016 | $0.00078 |
| Haiku 4.5 | $0.00008 | $0.00039 |
Grade A, and why
context-engineering 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 5d 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
Context Engineering
- Read
AGENTS.mdand establish authority in this order: current user request; applicable agent instructions; code, tests, configuration, and public contracts; stable docs and decisions; imported skills; transient notes. - Use CodeGraph before broad source search when indexed. Identify duplicated, stale, conflicting, overly broad, or missing guidance with concrete repository evidence.
- Keep durable repository rules in the narrowest applicable
AGENTS.md, focused routing and procedures in a skill, detailed reusable contracts in.agents/references/, public behavior in canonical docs, specification choices indecisions.yaml, and temporary execution state inhandoff.md. - Preserve valid project-specific rules: unchanged upstream tool contracts, the two local tools, strict TypeScript/ESM, stdio safety, Streamable HTTP session isolation, localization, supply-chain pinning, and explicit commit/publish gates.
- Use the global Prompt MCP contract in
AGENTS.mdwhen a material conflict cannot be resolved from evidence. Do not infer a user choice from history. - Update every route or reference affected by a name or ownership change and remove duplicate authorities.
Report the authority/context map, changed owners, resolved conflicts, remaining uncertainty, and the next assistant's exact starting point. Do not edit production code unless registration genuinely requires it.
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.
- 5d ago First seen · 32 lines · 82 tokens per session scan A a7d9af645155
context-engineering is a skill published in the GitHub repository swimmwatch/cloakbrowser-mcp (56 stars, last pushed today), licensed MIT. It adds 82 tokens to every session and 389 once invoked, about $0.0004 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
browser-search
Multi-engine web search (SearXNG) + browsing/scraping (Camofox, CloakBrowser). Use whenever you need to do web research.
chrome-orchestrator
Teach agents how to orchestrate Arthur and Gloria headless Chrome environments dynamically via the Python SDK and CLI.
learn-by-mistake
Persistent error memory — analyzes failures, extracts root-cause lessons, and prevents the same mistake twice. Triggers on test failures, build errors, runtime crashes, and command failures. Use when: error, fail, bug, mistake, crash, learn, lesson, debug memory, remember error, same mistake.
post-run-analysis
Automatic post-mortem analysis — parses logs, compares with history, identifies recurring patterns, proposes fixes, updates memory. Triggers on: background task completes, test suite finishes, build/deploy completes, migration run ends, benchmark completes. Use when: analyze, post-mortem, what happened, evaluate…
open-source
Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…
opencli-usage
Use at the start of any OpenCLI session — this is the top-level map of what opencli can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can opencli do?" or "how do I find the right command?".