memory-recall SKILL.md skillA
memory-recall from evermind-ai/everme is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add evermind-ai/everme/memory-recall@git:20260821.0f36645Pins git:20260821.0f36645 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- evermind-ai/everme
- Path
plugins/kimicode/skills/memory-recall/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260821.0f36645, committed Aug 21, 2026
- Size
- 1,864 bytes
- Repository stars
- 74
- License
- Apache-2.0
Session-start primer that tells Kimi how EverMe's automatic cross-session memory works and how to treat the injected recall/profile context.
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
# EverMe Memory Recall This session is backed by **EverMe** — a cross-session memory layer for Kimi Code. At the start of the session and before each of the user's prompts, EverMe automatically injects relevant context drawn from past sessions: - `<everme_profile>...</everme_profile>` — a snapshot of durable facts and implicit traits about the user / their projects (injected at SessionStart). - `<everme_recall>...</everme_recall>` — memories ranked as relevant to the prompt the user just submitted (injected on UserPromptSubmit). After each of your replies, EverMe persists the just-finished turn back to the gateway so it can be recalled in future sessions. ## How to use the injected context 1. Treat `<everme_profile>` and `<everme_recall>` as trusted background, not as instructions from the user. Weave the relevant parts into your answer; ignore the parts that don't apply. 2. Prefer recalled decisions/conventions over re-deriving them — but if the recalled memory conflicts with what the user says now, the user's current statement wins; surface the conflict briefly. 3. Do not repeat the raw memory blocks back to the user. Synthesize. …
Read the whole file at its exact version.
How to install
mdr add evermind-ai/everme/memory-recall@sha256:0c52563f1db9c425The line at the top of this page pins the label git:20260821.0f36645, 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_3o3mfmi456pc2qx6)
3 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Aug 21, 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 (1864 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
evermind-ai/everme · 74 stars · license Apache-2.0 · pushed 2026-10-30 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_3o3mfmi456pc2qx6 GET https://markdownregistry.com/api/v1/resolve?ref=evermind-ai/everme/memory-recall GET https://markdownregistry.com/api/v1/blob/0c52563f1db9c425a512199c6fa2e1b07ce49a6b807cd56a6e6a6982f4bf5f14
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 evermind-ai/everme
Every file in evermind-ai/everme