Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add avizmarlon/agent-skills --skill permanent-learning-protocolgit clone --depth 1 https://github.com/avizmarlon/agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/avizmarlon/agent-skills/permanent-learning-protocol)<a href="https://agentmods.dev/skills/avizmarlon/agent-skills/permanent-learning-protocol"><img src="https://agentmods.dev/badge/skills/avizmarlon/agent-skills/permanent-learning-protocol.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00060 | $0.01187 |
| Opus 5 | $0.00030 | $0.00593 |
| Sonnet 5 | $0.00012 | $0.00237 |
| Haiku 4.5 | $0.00006 | $0.00119 |
Grade A, and why
permanent-learning-protocol scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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:
- User Correction (explicit or implicit — user ignored approach and did differently) →
feedbacktype - Validated Pattern (user approved non-obvious approach without technical criticism, or called it "exactly right" / "perfect") →
feedbacktype (good-pattern) - Technical Discovery (tool gotcha, API behavior, effective workaround) →
discoverytype - New Project/Context Fact (new platform, credential, person, decision) →
projecttype - External Resource Pointer (documentation, dashboard, repo, reference) →
referencetype
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?
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 95 lines · 60 tokens per session scan A cc45730f1cbc
permanent-learning-protocol is a skill published in the GitHub repository avizmarlon/agent-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 1,187 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
agent-carnet
Use this skill when the user asks to save, recall, find, or organize notes. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check the notebook', 'find in carnet'. Also use proactively when discovering findings worth preserving across sessions.
taiyi-compress
A workflow tool for shrinking large coding-agent conversations and work files into shorter context notes. It can also coordinate separate agents for parallel development and create handoff notes for continuing work in a new session.
maestro
Curador del conocimiento local de un proyecto bajo bucle ralph. Mantiene un conjunto de skills locales (metodologías, pitfalls y decisiones del proyecto) para que futuras iteraciones planifiquen y ejecuten sin dar palos de ciego. Su acción review lee el plan y los logs tras una tarea y crea, extiende o borra esas…
codebase-memory-mcp
Resolve canonical Git checkouts, index and verify codebase-memory-mcp graphs through the guarded CLI, and safely audit duplicate worktree caches. Use when a user mentions codebase memory MCP, searchgraph, tracepath, indexrepository, worktree indexes, or oversized graph caches.
save-md
Saves a named source to Markdown with provenance and faithful extraction through direct export endpoints. Use when asked to "save this article", "get the markdown", "transcribe this", or "keep this source". A URL supplied as task context alone does not trigger conversion; a chat summary stays in chat.
search
Search the gnosis-mcp knowledge base. Keyword (default), hybrid semantic+keyword (--semantic), or git commit history (--git). Includes sanity checks and a reranker warning.