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 bikeread/promethos --skill design-agent-contextgit clone --depth 1 https://github.com/bikeread/promethosWrote 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/bikeread/promethos/design-agent-context)<a href="https://agentmods.dev/skills/bikeread/promethos/design-agent-context"><img src="https://agentmods.dev/badge/skills/bikeread/promethos/design-agent-context.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 5.1 | $0.00028 | $0.00609 |
| Opus 5 | $0.00014 | $0.00304 |
| Sonnet 5 | $0.00006 | $0.00122 |
| Haiku 4.5 | $0.00003 | $0.00061 |
Grade A, and why
design-agent-context 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 7d 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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
Give the agent the minimum useful context needed to perform well without overloading it or hiding critical information.
Inputs
- Agent task shape
- Available sources of truth
- Context window and retrieval constraints
Non-Goals
- Designing long-term memory policy in full
- Dumping every possibly relevant file into context
Workflow
Trigger signals
- Agent loads many files but still misses the relevant one
- Context window usage is high and growing
- User says "it keeps loading too much" or "why didn't it read the right file"
- The task is a long-running repo-maintenance or document-heavy workflow and the initial working set is starting to sprawl
- System prompt is getting long without a refresh or compression strategy
1. Define the task loop the agent must sustain
Describe the recurring loop the agent is performing so context choices can be judged against actual operational needs. Success criteria: Context design is anchored to a concrete task loop rather than a vague idea of "more context is better."
2. Identify the immediate working set
Choose the small set of facts, files, instructions, and state that must be present at the start of the loop. Success criteria: The initial context is justified, bounded, and clearly more important than deferred material.
3. Separate eager, deferred, and retrieved information
Classify what should always be loaded, what can be discovered on demand, and what should stay out of the active context entirely. Success criteria: The strategy distinguishes mandatory context from optional or expensive context.
4. Define source-of-truth and compression rules
State which representations are authoritative, when summaries may replace raw material, and when the agent must re-open original sources. Success criteria: Compression never silently becomes a substitute for the real source of truth.
5. Define refresh and reset behavior
Specify when context should be trimmed, refreshed, re-retrieved, or rebuilt from clean state. Success criteria: The agent has a plan for long-running usefulness rather than unchecked context accumulation.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 7d ago First seen · 79 lines · 28 tokens per session scan A 33e321722ea6
design-agent-context is a skill published in the GitHub repository bikeread/promethos (33 stars, last pushed 5mo ago), licensed MIT. It adds 28 tokens to every session and 609 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…