swarm-memory SKILL.md skillA
swarm-memory from chadixearth/graphyloop is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add chadixearth/graphyloop/swarm-memory@git:20261029.22f8bd5Pins git:20261029.22f8bd5 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- chadixearth/graphyloop
- Path
integrations/claude-code/skills/swarm-memory/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261029.22f8bd5, committed Oct 29, 2026
- Size
- 3,606 bytes
- Repository stars
- 3
- License
- MIT
Use this skill at the start and end of every non-trivial task to recall and record durable project knowledge through graphyloop memory - what to search before planning, what is worth storing, what must never be stored, and how to correct a wrong memory.
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
# Swarm memory
Memory is only useful if it is read before deciding and written after learning.
A store that is written but never searched is a diary; one that is searched but
never corrected repeats its mistakes forever.
## When to activate
- START of any non-trivial task, in the same parallel block as the first reads and before the context pack and contract. A trivial single-file edit skips memory.
- END of any task that produced a decision, a gotcha, or a reusable approach.
- When a past decision is being revisited ("why is it done this way?").
## Procedure
1. **Recall first.** `memory_search` with 2-4 concrete keywords from the task
(component names, error text, feature nouns). Optional `type` filter:
`decision`, `pattern`, `lesson`, `event`, `task`.
- Results exist → use them, and say which memory informed the plan.
- Nothing → say nothing and proceed. Never invent a recalled memory.
2. **Store at the end, one entry.** `memory_store` with the right type:
- `decision` — a choice made and why (the alternative rejected matters more than the choice).
- `lesson` — a gotcha hit and how it was resolved. This is the highest-value type.
…Read the whole file at its exact version.
How to install
mdr add chadixearth/graphyloop/swarm-memory@sha256:043bdb3e031ae213The line at the top of this page pins the label git:20261029.22f8bd5, 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.
[](https://markdownregistry.com/a/art_uzcub4ay6n44m4lc)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 29, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3606 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
chadixearth/graphyloop · 3 stars · license MIT · pushed 2026-11-02 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_uzcub4ay6n44m4lc GET https://markdownregistry.com/api/v1/resolve?ref=chadixearth/graphyloop/swarm-memory GET https://markdownregistry.com/api/v1/blob/043bdb3e031ae213d536eb5f6a1b777ce07bc8260e8024d19535a37d4a8b4108
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.