latent-briefing SKILL.md skillA

latent-briefing from muratcankoylan/agent-skills-for-context-engineering is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add muratcankoylan/agent-skills-for-context-engineering/latent-briefing@git:20260629.8fc51c7

Pins git:20260629.8fc51c7 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
muratcankoylan/agent-skills-for-context-engineering
Path
skills/latent-briefing/SKILL.md
Versions recorded
3
Latest version
git:20260629.8fc51c7, committed Jun 29, 2026
First version recorded
Apr 14, 2026
Size
13,029 bytes
Repository stars
18,377
License
MIT

This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent", "orchestrator worker context", "latent briefing", "reduce worker tokens", "cross-agent memory without summarization", or discusses Attention Matching compaction, recursive language models with workers, or token explosion in hierarchical agents.

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

# Latent Briefing and KV Cache Memory Sharing

Hierarchical multi-agent systems often pay for the same context twice. The orchestrator accumulates a long reasoning trajectory, but each worker usually receives only a narrow text handoff such as a subtask prompt plus raw document slices. Passing the full trajectory fixes coverage but drives token cost up on every worker call. Summarization introduces latency and information loss. Retrieval helps with document access but does not preserve the orchestrator's evolving reasoning state.

Latent Briefing addresses this by sharing memory at the **representation level** rather than the text level. The core idea is to compact the orchestrator trajectory in the worker model's KV cache, keeping positions that are most relevant to the **current worker task**. The method builds on **Attention Matching (AM)** KV cache compaction and adapts it for inference-time multi-agent handoff with task-guided queries, a shared token mask across heads, and robust thresholding.

## When to Activate

Activate this skill when:
…

Read the whole file at its exact version.

How to install

No tool to install first
claude plugin marketplace add https://markdownregistry.com/mp/a/art_x3iube7penlcp6s5/d84e7abe51f037a353dc3ccf18498498099fc633373a0d223bd6cc45277fd0bd.json

Then /plugin install latent-briefing@markdownregistry-x3iube7penlcp6s5 in Claude Code. It installs git:20260629.8fc51c7, the one graded A here, pinned to the commit it was graded at, and leaves it there.

The exact contents, by fingerprint
mdr add muratcankoylan/agent-skills-for-context-engineering/latent-briefing@sha256:d84e7abe51f037a3

The line at the top of this page pins the label git:20260629.8fc51c7, 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 badge

[![mdr](https://markdownregistry.com/badge/art_x3iube7penlcp6s5.svg)](https://markdownregistry.com/a/art_x3iube7penlcp6s5)

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

Ask from your agent
claude mcp add --transport http markdownregistry https://markdownregistry.com/mcp/registry

Then ask it: what changed in muratcankoylan/agent-skills-for-context-engineering/latent-briefing since the version I have? It reads every saved version here, no key and no account. Any agent that speaks MCP can add it.

Got a copy of latent-briefing from somewhere else? Ask it: where did my latent-briefing come from, and what was changed? It names the public original, the version yours is closest to and every changed line. The text is not kept.

Versions

The registry has recorded 3 versions of this file, between Apr 14, 2026 and Jun 29, 2026, about one every 38 days.

Watch this file (sign in, one email per new version)

versioncommittedcommitsizeaudit
git:20260629.8fc51c7 latest2026-06-29 8fc51c7 13,029 BA view · diff
git:20260519.cbc2c972026-05-19 cbc2c97 13,015 BA view · diff
git:20260414.60d36c22026-04-14 60d36c2 12,205 BA view
Keep it current by itself, install once

Committed this skill to a repository? Install the markdownregistry skill updates app on it, or on all of them. When the registry saves a newer version, a pull request brings your copy to it within minutes, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

Install on GitHub

It asks to read and write contents and pull requests, and to read metadata. No workflow file, no Actions setting, nothing runs on your runners. Uninstall it and everything the registry kept about your repository is deleted.

Keep it current by itself

Committed this skill to a repository? Add one workflow file, and when a newer version is saved, a pull request brings your copy to it, the newest version first, then what changed and any check it newly trips. A copy you edited is never touched, and nothing is deleted.

mkdir -p .github/workflows && curl -fsSL https://markdownregistry.com/ci/skill-updates.yml -o .github/workflows/skill-updates.yml

It runs daily on GitHub Actions, no key and no account. Read the workflow before you add it.

Check a whole project

From the root of your project, one line hashes each installed skill's SKILL.md, your AGENTS.md and your CLAUDE.md, and asks the registry once. Only the fingerprints and paths are sent.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --data-binary @- https://markdownregistry.com/api/v1/check-copies

In CI, add --fail-with-body: the answer is 409 when any file is behind, so the step fails and still prints which files.

sha256sum .claude/skills/*/SKILL.md AGENTS.md CLAUDE.md | curl -s --fail-with-body --data-binary @- https://markdownregistry.com/api/v1/check-copies

No sha256sum on your machine? shasum -a 256 prints the same lines.

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 (13029 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

muratcankoylan/agent-skills-for-context-engineering · 18,377 stars · license MIT · pushed 2026-10-12 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_x3iube7penlcp6s5
GET https://markdownregistry.com/api/v1/resolve?ref=muratcankoylan/agent-skills-for-context-engineering/latent-briefing
GET https://markdownregistry.com/api/v1/blob/d84e7abe51f037a353dc3ccf18498498099fc633373a0d223bd6cc45277fd0bd

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 muratcankoylan/agent-skills-for-context-engineering

AGENTS.md AGENTS.md file
muratcankoylan/agent-skills-for-context-engineering · AGENTS.md
git:20261001.831ea13 · audit A · 18,377 stars
CLAUDE.md CLAUDE.md file
muratcankoylan/agent-skills-for-context-engineering · CLAUDE.md
git:20261001.831ea13 · audit A · 18,377 stars
context-engineering-collection SKILL.md skill
muratcankoylan/agent-skills-for-context-engineering · SKILL.md · A comprehensive collection of Agent Skills for context engineering, harness engineering, multi-agent architectures, and…
git:20261012.9f87ab2 · audit A · 18,377 stars
book-sft-pipeline SKILL.md skill
muratcankoylan/agent-skills-for-context-engineering · examples/book-sft-pipeline/SKILL.md · This skill should be used for book-to-SFT pipelines: ePub extraction, literary segmentation, author-voice dataset…
v2.0.0 · audit A · 18,377 stars
digital-brain SKILL.md skill
muratcankoylan/agent-skills-for-context-engineering · examples/digital-brain-skill/SKILL.md · This skill should be used for personal operating-system workflows: content creation, voice consistency, relationship…
v1.0.0 · audit A · 18,377 stars
AGENTS.md@examples/digital-brain-skill/agents AGENTS.md file
muratcankoylan/agent-skills-for-context-engineering · examples/digital-brain-skill/agents/AGENTS.md · Automation scripts and agent helpers for the Digital Brain. Use these scripts for recurring tasks, summaries, and…
git:20251230.ace9c0a · audit A · 18,377 stars
reasoning-trace-optimizer SKILL.md skill
muratcankoylan/agent-skills-for-context-engineering · examples/interleaved-thinking/SKILL.md · Debug and optimize AI agents by analyzing reasoning traces, context degradation, tool confusion, instruction drift…
git:20260515.0d7595d · audit A · 18,377 stars
comprehensive-research-agent SKILL.md skill
muratcankoylan/agent-skills-for-context-engineering · examples/interleaved-thinking/generated_skills/comprehensive-research-agent/SKILL.md · Ensure thorough validation, error recovery, and transparent reasoning in research tasks with multiple tool calls
git:20260629.8fc51c7 · audit A · 18,377 stars
advanced-evaluation SKILL.md skill
muratcankoylan/agent-skills-for-context-engineering · skills/advanced-evaluation/SKILL.md · This skill should be used for advanced LLM evaluation: LLM-as-judge systems, direct scoring, pairwise comparison…
git:20260629.8fc51c7 · audit A · 18,377 stars
bdi-mental-states SKILL.md skill
muratcankoylan/agent-skills-for-context-engineering · skills/bdi-mental-states/SKILL.md · This skill should be used when modeling agent mental states with BDI concepts: beliefs, desires, intentions…
git:20260629.8fc51c7 · audit A · 18,377 stars
context-compression SKILL.md skill
muratcankoylan/agent-skills-for-context-engineering · skills/context-compression/SKILL.md · This skill should be used when long-running agent sessions need context compression, structured summarization…
git:20261001.7638f30 · audit A · 18,377 stars
context-degradation SKILL.md skill
muratcankoylan/agent-skills-for-context-engineering · skills/context-degradation/SKILL.md · This skill should be used for diagnosing and mitigating context degradation: lost-in-middle failures, context…
git:20260629.8fc51c7 · audit A · 18,377 stars

Every file in muratcankoylan/agent-skills-for-context-engineering

Other files named latent-briefing

latent-briefing SKILL.md skill
docxology/template · .agents/skills/latent-briefing/SKILL.md · This skill should be used when the user asks to "share memory between agents", "KV cache compaction for multi-agent"…
git:20260713.397aa15 · audit A · 24 stars

Browse by kind, by grade A, or by owner.