Home / nahid-sparktales / agent-dispatcher · GitHub

context-engineering SKILL.md skillA

context-engineering from nahid-sparktales/agent-dispatcher is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add nahid-sparktales/agent-dispatcher/context-engineering@git:20260919.a0d4f55

Pins git:20260919.a0d4f55 in mdr.lock. Pin the fingerprint instead.

Audit grade: A, 17 of 17 checks passed
Kind: SKILL.md skill
Repository: nahid-sparktales/agent-dispatcher
Path: skills/ai/context-engineering/SKILL.md
Versions recorded: 1
Latest version: git:20260919.a0d4f55, committed Sep 19, 2026
Size: 6,448 bytes
Repository stars: 58
License: MIT

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…

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file 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
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add nahid-sparktales/agent-dispatcher/context-engineering@sha256:76f0a60942f5fdca

The line at the top of this page pins the label git:20260919.a0d4f55, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_4dho442fatdw5toj.svg)](https://markdownregistry.com/a/art_4dho442fatdw5toj)

5 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Sep 19, 2026.

version	committed	commit	size	audit
git:20260919.a0d4f55 latest	2026-09-19	a0d4f55	6,448 B	A	view

Audit of the latest version

A 17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (6448 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag

Source

GitHub

nahid-sparktales/agent-dispatcher · 58 stars · license MIT · pushed 2026-10-24 · branch main

API

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 AI assistant 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.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from nahid-sparktales/agent-dispatcher

agent-dispatcher SKILL.md skill

nahid-sparktales/agent-dispatcher · skills/agent-dispatcher/SKILL.md · Handle requested Agent Dispatcher work with direct execution or prepared specialist guidance. Includes named roles…

git:20260926.d1b76c1 · audit A · 58 stars

agent-design SKILL.md skill

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…