ai-memory-durable-pages
Skill0 starsChanged 3 months agoMITView on GitHub
Use this skill for any explicit wiki mutation in ai-memory: saving durable or time-bounded project knowledge, recording a rule or annotation, updating a note, or deleting a memory page. Trigger by semantic intent rather than exact wording; routine session capture is not a durable-page request.
2 other projects use a version of this, 2 of them edited.
Adopted by
Most recently taken up by
- ton-anywhere/my-favorite-promptsedited, first seen Nov 8, 2026
- lucas-Oliveira-01/agentsedited, first seen Sep 28, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 2
- ton-anywhere/my-favorite-prompts★ 447% same
- lucas-Oliveira-01/agents★ 179% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ai-memory-handoffSkill
- ai-memory-learning-maintenanceSkill
- ai-memory-retrievalSkill
- ai-memory-routing-installSkill
- avc-amendSkill
- avc-build-sliceSkill
- avc-freeze-oracleSkill
- avc-live-qaSkill
- avc-retroSkill
- avc-reviewSkill
- avc-scoutSkill
- avc-spikeSkill
- avc-startSkill
- avc-verifySkill
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
- Distinctive: line 9
Use this skill only for deliberate durable wiki mutations.
- Distinctive: line 18
Write a page only when the user explicitly asks to remember something permanently, save a note, add an annotation, or record project …
- Very specific: line 22
When the user explicitly wants a note to be temporary, pass expires_at as an RFC3339 instant or a bare YYYY-MM-DD (the end of that day in …
- Distinctive: line 34
Delete only by exact path.
- Distinctive: line 38
Default to the current project.
- Very specific: line 42
When the user asks to record an architectural decision (a chosen approach, a rejected alternative, a standing trade-off), write it as a …
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
<!-- ai-memory-managed: routing-skill -->ai-memory durable pages
Use this skill only for deliberate durable wiki mutations. Routine session capture is automatic, and permanent notes require an explicit user request.
Tools in this cluster
memory_write_pagewrites a durable wiki page for permanent project knowledge.memory_delete_pageremoves a durable wiki page by exact path.
Writing durable memory
Write a page only when the user explicitly asks to remember something permanently, save a note, add an annotation, or record project knowledge. Do not use durable pages for transient progress, normal status updates, or next-session context.
Put the page title as a # H1 on the first line of the body and omit the separate title argument. ai-memory derives the title from that H1. Keep the content concise and fact-like, with enough context that a future agent can apply it without rereading the whole session.
When the user explicitly wants a note to be temporary, pass expires_at as an
RFC3339 instant or a bare YYYY-MM-DD (the end of that day in UTC). After the
TTL, normal search, recent, and briefing reads hide the page; the next forget
sweep deletes it. A TTL outranks pinned, so do not combine them unless the user
has deliberately requested that behavior.
Project rules belong in instructions first
If the user asks to create a durable project rule such as always do X or never do Y, update the project's canonical agent instruction file when the repository says one exists. Use a durable page only when the user explicitly wants the rule in the wiki too, or when no canonical instruction file applies.
Deleting durable memory
Delete only by exact path. If the user gives a vague title or topic, first resolve it to the page path using read-only lookup. Preserve sibling projects unless the user explicitly names them.
Scope default
Default to the current project. Pass workspace and project together only when the user explicitly names a different project. Never pass scope arguments for phrases like this project, here, we, or our work.
Architectural decisions get ADR structure and a pin
When the user asks to record an architectural decision (a chosen approach, a rejected alternative, a standing trade-off), write it as a durable page under decisions/<short-slug>.md with pinned: true and this structure in the body:
# <Decision title>
**Status:** accepted <!-- proposed | accepted | superseded by [[decisions/other]] -->
## Context
What situation forced a decision; the constraints that mattered.
## Decision
What was decided, stated as a fact.
## Consequences
What becomes easier, what becomes harder, what was given up.
Rejected alternatives and WHY, so future sessions don't re-propose them.Pinned pages are exempt from retention decay and curation, and the auto-improvement path refuses to rewrite them — the record stays immutable unless a human unpins it. To supersede a decision, write a NEW page and set the old page's status line to superseded by [[decisions/<new>]]; never edit the old decision's substance. Note: ai-memory never touches files in the project repository — a docs/adr/ directory managed there (by hand or by another tool) is outside ai-memory entirely; these wiki ADRs complement it for cross-session retrieval.
Standing user/team preferences go to the global scope
When the fact is a standing preference that should apply to EVERY project — technology choices ("always use pnpm workspaces"), code style ("prefer composition over inheritance"), personal conventions ("never --force without asking") — call memory_write_page with scope: "global" instead of the current project. The page lands in the reserved _global scope, and default memory reads surface it in every project as global_scope_hits. scope: "global" cannot be combined with workspace/project arguments. Use it only for genuinely cross-project preferences; project-specific rules stay in the project (or its instruction file, per the section above).
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
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.

