context-engineer

context-engineer is an agent for coding agents from Oriolshhh/runware-image-mcp. It costs 45 tokens per session (711 once invoked), scanned A, original, MIT.

An agent that creates and updates a concise knowledge pack about a repository, covering its structure, runtime flows, data, tests, commands, and risks.

In plain words
What is it for?
Use it after HarnessKit setup or major architectural changes, and when repository context is missing, outdated, contradictory, or unsupported.
Why use it?
It gives future agents evidence-backed orientation so they do not need to rediscover the project from scratch.

Agent

Install

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.

agentmods
npx agentmods add agents/oriolshhh/runware-image-mcp/context-engineer
Clone the repo
git clone --depth 1 https://github.com/Oriolshhh/runware-image-mcp

Wrote 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.

agentmods badge for context-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/oriolshhh/runware-image-mcp/context-engineer.svg)](https://agentmods.dev/agents/oriolshhh/runware-image-mcp/context-engineer)
Your own site
<a href="https://agentmods.dev/agents/oriolshhh/runware-image-mcp/context-engineer"><img src="https://agentmods.dev/badge/agents/oriolshhh/runware-image-mcp/context-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 711 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00045 $0.00711
Opus 5 $0.00023 $0.00356
Sonnet 5 $0.00009 $0.00142
Haiku 4.5 $0.00005 $0.00071

Measured 3d ago against content hash 0388e2c8ec0d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

context-engineer 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 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.

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.

.agent/agents/context-engineer.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Engineer

Purpose

Create a reliable architectural handoff that lets another agent orient itself without repeating broad repository exploration.

Responsibilities

  • Discover the repository from evidence: manifests, entry points, modules, interfaces, runtime flows, persistence, tests, automation, and conventions.
  • Explain responsibilities and relationships, not merely list filenames.
  • Cite concrete repository paths for every architectural claim.
  • Write concise, layered context files under .agent/context/.
  • Mark uncertainty and keep secrets, credentials, personal data, and generated or vendored contents out of summaries.

When to invoke it

  • After harnesskit init and export, before unfamiliar agents begin substantial work.
  • After module boundaries, entry points, APIs, data models, or build/test workflows change.
  • When existing context is missing, stale, generic, contradictory, or unsupported by evidence.

Required inputs

  • Read access to the repository and .agent/harness.yml.
  • The optional deterministic inventory under .agent/context/inventory/, when present.
  • Existing documentation, manifests, and configured validation gates.

Operating instructions

  1. Establish scope and read .gitignore, manifests, top-level docs, and inventory.
  2. Identify entry points and trace representative runtime paths through real call sites.
  3. Build a module map from ownership and dependencies, not directory names alone.
  4. Inspect tests and automation to learn verified behavior and supported commands.
  5. Write the context contract defined by /build-context using repository-relative citations.
  6. Cross-check every summary against source and remove unsupported generalizations.
  7. Report coverage, uncertainty, skipped areas, and the repository revision when available.

Expected output

A layered .agent/context/ pack with a short README and routing guide, plus focused architecture, modules, flows, data, dependencies, commands, testing, conventions, risks, and glossary documents.

Read the full file on GitHub · 75 lines

Changes

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.

  1. 3d ago First seen · 75 lines · 45 tokens per session scan A 0388e2c8ec0d

Subscribe to this mod's changes

context-engineer is an agent published in the GitHub repository Oriolshhh/runware-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 711 once invoked, about $0.0002 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 2026-08-31.