# Permanent Learning Protocol

> Permanent learning — AI agent proposes learnings from sessions, user approves in chat, integrations saved to auto-loaded files. Triggers on session end or manual /learn command. Use when consolidating discoveries, user says learn/consolidate/document, or end-of-session signals.

- **Type:** Skill
- **Install:** `agentstack add skill-avizmarlon-agent-skills-permanent-learning-protocol`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [avizmarlon](https://agentstack.voostack.com/s/avizmarlon)
- **Installs:** 0
- **Category:** [AI & ML](https://agentstack.voostack.com/c/ai-and-ml)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [avizmarlon](https://github.com/avizmarlon)
- **Source:** https://github.com/avizmarlon/agent-skills/tree/main/skills/permanent-learning-protocol

## Install

```sh
agentstack add skill-avizmarlon-agent-skills-permanent-learning-protocol
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

## Permanent Learning Protocol

AI agents evolve only if learnings become part of their permanent instruction layer — auto-loaded in every future session. Session-only memory does not persist; only auto-loaded files survive across sessions.

This protocol moves learnings from chat to durable instruction files, with explicit user approval at each step. It prevents silent integration and ensures transparency.

### 1. Triggers

**Automatic (natural session end — inferred from tone/context):**
- Farewell signals (goodbye, thanks + session ending, "signing off")
- Gratitude + user disappears
- Clear pivot to unrelated topic after coherent work block
- Request to open new session / create handoff / create worktree for next phase
- Session approaching context limit

**Manual:** User invokes skill `/learn`, or says variations like "consolidate what you learned this session" / "what did you discover today?"

### 2. Agent Action — Reflection + Proposal in Chat

Quick scan across learning categories:

1. **User Correction** (explicit or implicit — user ignored approach and did differently) → `feedback` type
2. **Validated Pattern** (user approved non-obvious approach without technical criticism, or called it "exactly right" / "perfect") → `feedback` type (good-pattern)
3. **Technical Discovery** (tool gotcha, API behavior, effective workaround) → `discovery` type
4. **New Project/Context Fact** (new platform, credential, person, decision) → `project` type
5. **External Resource Pointer** (documentation, dashboard, repo, reference) → `reference` type

**Present in chat as numbered proposal — DO NOT save yet:**

```
📚 Proposed permanent learnings:

1. [feedback] User prefers X over Y
   Location: global-instructions.md (global scope)
   Why: incident from session / concrete reason
   How to apply: when/where to use this pattern

2. [discovery] Tool Z has gotcha W
   Location: project docs or global reference
   Type: behavioral / limitation / workaround

Approve all? Reject item N? Discuss any?
```

### 3. User Response

- **"ok" / "approved" / "yes" / "go" / "save":** Agent integrates **permanently** into files listed above in the same session. No follow-up. No "will do later".
- **"reject N" / "remove N" / "keep only 1 and 3":** Skip rejected items, integrate the rest.
- **"discuss" / asks question:** Converse before integrating.
- **No response (session closes):** Agent writes the proposal to `/_pending-approval.md` (project scope) or global pending file (global scope). On next session, agent reads this file at start — if pending items exist, re-present in chat before proceeding.

### 4. Storage Destinations by Learning Type

| Learning Type | Primary Destination | Cross-Tool Mirror |
|---|---|---|
| Global operating preference | global-instructions.md | equivalent in all agent instruction files |
| Project-specific behavioral rule | `/.agent-rules/.md` | `.cursor/rules/.mdc`, mention in project instruction file |
| Workflow / process pattern | dedicated rule file + note in global if cross-project | mirror as above |
| Architecture decision | `docs/adr/ADR-NNN.md` + update `docs/architecture.md` | entry in `CHANGELOG.md` |
| Reusable technical discovery | `docs/.md` in project | entry in `CHANGELOG.md` |
| Discrete fact about project/context | memory file (`/_memory/.md`) + entry in memory index | — |
| External resource pointer | reference memory file + index entry | — |

### 5. Anti-Patterns (Prohibited)

- Silent integration without showing in chat — breaks approval contract. Permanent memory without approval = unilateral decision.
- Trigger on fixed keyword user must memorize ("learn now", "save this") — user should never have to remember special syntax.
- Duplicate entries instead of updating existing file (always check index/file before creating new).
- Save ephemeral or trivial facts ("today I ran `git status`", "session ended at 3 PM"). Only substantive learnings.
- Invent learnings to appear productive. If nothing substantive happened, "no new learnings this session" is the correct response.
- Wait until next session to integrate — no future agent with this chat history will exist.
- Save rule without **Why** and **How to apply** — becomes dogma. Future agents won't know how to judge edge cases.

### 6. Standards for Quality Learnings

A learning is worth saving if:
- It changes how an agent will operate on future tasks (new rule, new workaround, new gotcha)
- It discovered something non-obvious (not trivial to deduce from first principles)
- It applies to multiple projects or use cases
- It represents consensus after uncertainty or disagreement

A learning is NOT worth saving if:
- It's a one-time fact tied to this specific project/session
- It's restating the manual/docs (user should read them)
- It's generic best practice already documented elsewhere

### Applies to

All AI agents in a skill system, every project, every session. Part of the standard agent bootstrap and lifecycle.

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [avizmarlon](https://github.com/avizmarlon)
- **Source:** [avizmarlon/agent-skills](https://github.com/avizmarlon/agent-skills)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-avizmarlon-agent-skills-permanent-learning-protocol
- Seller: https://agentstack.voostack.com/s/avizmarlon
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.