agentleFS
DeiblerDeibler/edmund-harness/skills/history/SKILL.md

history

Skill24 starsChanged 2 months agoMITView on GitHub

Research past messages and shared files in the current iMessage conversation.

14 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 12 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Don't over-fetch: If your working memory (from --resume) already has the answer, skip the tool.

    line 50

“Common” is measured: kept by at least 6 in 10 of the 12 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

history

The edmund-harness MCP server exposes three read-only tools scoped to the current conversation (group chat, or DM contact including any aliased handles):

When to use

  • User references something "earlier," "yesterday," "that photo," "what I said about X"
  • You need to ground a reply in concrete prior context (not just your working memory)
  • A group question needs specific recall ("who suggested Friday?")
  • User sends a follow-up about a file or image they shared previously

Tools

search_history(query?, sender?, since?, until?, limit?)

Substring search + metadata filters. Returns msg_guid ISO-time Sender: text. Use a tight limit (default 50) to keep results readable.

search_history(query="Friday plans")
search_history(sender="+15550100001", since="2026-04-15")
search_history(since="2026-04-18T00:00:00Z", limit=30)

get_message(msg_guid)

Full text + attachment paths for a single message from the search results. Use when the preview was truncated or you need attachment paths.

list_attachments(mime_prefix?, since?, sender?, limit?)

List images/audio/files shared in this chat. Returns absolute paths. Pair with the built-in Read tool to actually view an image.

list_attachments(mime_prefix="image/", limit=20)
list_attachments(since="2026-04-01")

Patterns

User: "pull up the photo riley sent last week"

  1. list_attachments(mime_prefix="image/", sender="<riley's handle>", since="<7 days ago>")
  2. Read the file path
  3. Reply based on what you saw

User: "what did jordan say about the api?"

  1. search_history(query="api", sender="+15550100001", limit=10)
  2. Summarize the hits in the reply

Don't over-fetch. If your working memory (from --resume) already has the answer, skip the tool. Only search when you're missing context.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.