context-engineering is agent-read markdown (skill) from nahid-sparktales/agent-dispatcher: Decide what actually occupies the model's window — progressive disclosure through an index, retrieval versus inlining, what compaction must preserve, and what loading everything costs. Use when a prompt or agent pulls in many files, docs or tool transcripts, when quality decays over a long session, when choosing between fetching at runtime and pasting up front, or when a context has to be trimmed or summarized. Not for the wording of the prompt, not for an agent's job and tool boundaries, and no.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# Context engineering
Loading everything is not thoroughness. It buries the instruction that mattered, raises cost on
every turn, and makes the failure look like a model problem instead of a packing problem.
## When this fires
When a prompt, agent or session loads substantial material, or when material has to be dropped.
It does not fire for a short prompt with fixed, small inputs.
## Procedure
1. **Measure before trimming.** List what is loaded each turn and how large each block is, biggest
first. Trimming by intuition removes the piece that was doing the work. If the runtime gives no
accounting, approximate it and say the numbers are approximate.
2. **Classify every block by when it is needed.** Always — the task and the output contract.
Sometimes — loaded when a stated condition holds. On demand — fetched by name only when a step
calls for it. A block that fits none of these is not needed; drop it and see what breaks.
3. **Build the index that makes disclosure possible.** A short list of what exists, what each thing
is for, and when it applies — written so the choice can be made without reading the thing
…
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
GET https://markdownregistry.com/api/v1/artifacts/art_4dho442fatdw5toj
GET https://markdownregistry.com/api/v1/resolve?ref=nahid-sparktales/agent-dispatcher/context-engineering
GET https://markdownregistry.com/api/v1/blob/76f0a60942f5fdca53db2ba2881904ba952de133c7acff9837fbfc96c1950fd7
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
nahid-sparktales/agent-dispatcher · skills/agent-dispatcher/SKILL.md · Route work to a specialist role and load its task-specific guidance. Use when the user invokes /agent-dispatcher, names…
nahid-sparktales/agent-dispatcher · skills/ai/agent-design/SKILL.md · Scope an agent or subagent before it is built — the one job it owns, the smallest tool set that closes that job, what…
nahid-sparktales/agent-dispatcher · skills/ai/agent-evals/SKILL.md · Build an eval suite that can actually detect a regression — cases pulled from real traffic, graders that check…
nahid-sparktales/agent-dispatcher · skills/ai/llm-observability/SKILL.md · See what an agent actually did — one trace per run with nested model, tool and retrieval spans, token and latency…
nahid-sparktales/agent-dispatcher · skills/ai/mcp-design/SKILL.md · Build an MCP server, or bring an existing one into a project — choosing the transport, deciding which tools, resources…
nahid-sparktales/agent-dispatcher · skills/ai/memory-design/SKILL.md · Decide what an agent should remember, which layer holds it, who it is scoped to, and how a stale or contradicted memory…
nahid-sparktales/agent-dispatcher · skills/ai/model-routing/SKILL.md · Pick a model per job and degrade sensibly when one fails — a quality bar per call site, candidates compared on the same…
nahid-sparktales/agent-dispatcher · skills/ai/prompt-engineering/SKILL.md · Write or revise a prompt so it holds up — output contract, instruction placement, examples that earn their place, an…
nahid-sparktales/agent-dispatcher · skills/ai/prompt-injection-defense/SKILL.md · Treat everything an agent reads but did not author as data rather than instructions — an explicit trust boundary, a…
nahid-sparktales/agent-dispatcher · skills/ai/retrieval-rag/SKILL.md · Build and fix retrieval that actually returns the right passage — structure-aware chunking, one pinned embedding model…
nahid-sparktales/agent-dispatcher · skills/ai/structured-output/SKILL.md · Get parseable, trustworthy structured results out of a model — schema design, the enforcement mechanism the provider…
nahid-sparktales/agent-dispatcher · skills/ai/tool-design/SKILL.md · Design the tools a model calls — names, parameter shapes, what a result returns, and error text written as an…
addyosmani/agent-skills · skills/context-engineering/SKILL.md · Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching…
a5c-ai/babysitter · library/methodologies/gsd/skills/context-engineering/SKILL.md · Context window monitoring and budget management. Keeps orchestrator at 15-30% context usage while subagents get full…
shashankswe2020-ux/whoop-mcp · .github/skills/context-engineering/SKILL.md · Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching…
habitat-thinking/ai-literacy-superpowers · ai-literacy-superpowers/skills/context-engineering/SKILL.md · This skill should be used when the user asks about "writing conventions", "codebase context", "HARNESS.md context…
aaaaqwq/agi-super-team · plugins/agi-super-team-codex/skills/context-engineering/SKILL.md · Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching…