agentleFS
chuckplayerchuckplayer/claude-agent-pack/skills/memory-query/SKILL.md

memory-query

Skill8 starsChanged 35 days agoMITView on GitHub

Search project memory files for a specific topic, decision, or constraint and return matching entries with citations. Use when you need to find what was decided about X, why Y was chosen, or whether Z is a known issue. Trigger this when someone says: what do we know about X, was there a decision about Y, check memory for Z, find the memory entry for X, what did we decide about Y, look up memory for X. Do NOT use for a full memory hygiene pass — use /memory-audit instead.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

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

    Search the project's memory/ directory for entries relevant to a specific topic, decision, or constraint.

    line 8
  2. Very specific:

    If memory/ does not exist in the current project, report that and stop.

    line 10
  3. Distinctive:

    If no active memory files match the query, say so explicitly:

    line 52
  4. Distinctive:

    Never hallucinate a memory entry.

    line 56
  5. Distinctive:

    Partial matches: If a file mentions the topic in passing but does not contain a decision about it, include it with a note that it is …

    line 61
  6. Distinctive:

    Multiple conflicting active files: If two active files at the same scope contradict each other, surface both and flag the conflict rather …

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “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

Memory Query

Search the project's memory/ directory for entries relevant to a specific topic, decision, or constraint. Returns matching entries with file paths and direct quotes.

If memory/ does not exist in the current project, report that and stop.

1. Discover active memory files

Glob("memory/**/*.md")

Filter to active files only — skip any file where the frontmatter contains status: superseded or status: archived. These are history and should not be surfaced as current answers.

2. Read and match

Triage on the filename first. Filenames follow YYYY-MM-DD-{prefix}-brief-slug.md, so the slug is a usable summary of the entry and every file has one. Read the full body of any file whose slug — or whose subdirectory — suggests relevance to the query.

description: is an optional frontmatter field present in only a minority of files. Use it as a second signal where it happens to exist; never rely on it being there, and never skip a file because it lacks one.

Memory-file frontmatter carries no summary-name key. One was removed on 2026-09-02 because it duplicated the filename. (This SKILL.md's own frontmatter is skill metadata, unrelated to the memory dialect.)

Match the file to the query if it:

  • Directly names the topic, technology, module, or pattern the user asked about
  • Contains a decision, rationale, or constraint related to the query
  • Documents a known issue or workaround for the queried area

3. Return results

For each matching file, output:

**[memory type] — [file path]**
> "[direct quote from the most relevant section]"

Summary: [one sentence describing what this memory says about the query topic]

Group results by memory type (decisions, architecture, context, known-issues) if multiple files match.

If no active memory files match the query, say so explicitly:

No active memory entries found for "[query]". If a decision was made, it may not have been recorded yet — consider running /memory-audit to identify gaps.

Never hallucinate a memory entry. If the content is not in a file, it does not exist.

Gotchas

  • Superseded and archived files are history only: Do not surface them as current answers, even if they are relevant to the query. If a superseded file would have answered the question, note that the topic was once addressed but is now superseded and point to the superseded-by: file if present. That field is sometimes prose rather than a filename, so read it before citing it as a file.
  • Partial matches: If a file mentions the topic in passing but does not contain a decision about it, include it with a note that it is contextual rather than a direct answer.
  • Multiple conflicting active files: If two active files at the same scope contradict each other, surface both and flag the conflict rather than picking one silently.

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.