Borrowing it
Nothing to install: this file belongs to moberghr/mtk-agent-toolkit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/moberghr/mtk-agent-toolkit/main/.claude/skills/promote-lesson/SKILL.mdgit clone --depth 1 https://github.com/moberghr/mtk-agent-toolkitWrote 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/moberghr/mtk-agent-toolkit/promote-lesson)<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/promote-lesson"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/promote-lesson/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/moberghr/mtk-agent-toolkit/promote-lesson"><img src="https://agentmods.dev/badge/skills/moberghr/mtk-agent-toolkit/promote-lesson.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00042 | $0.02473 |
| Opus 5 | $0.00021 | $0.01236 |
| Sonnet 5 | $0.00008 | $0.00495 |
| Haiku 4.5 | $0.00004 | $0.00247 |
Grade A, and why
promote-lesson scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Promote Lesson
Overview
Personal lessons are gitignored or live outside the repo entirely — they belong to the engineer, not the team. When one matures into a rule every contributor should follow, promote it to the committed tasks/lessons.md. This skill is the explicit, audited path for that move.
Two personal stores feed it, and the second is easy to forget precisely because MTK does not own it:
.claude/lessons/personal.md— MTK's own personal store.${CLAUDE_CONFIG_DIR:-~/.claude}/projects/<sanitized-cwd>/memory/— Claude Code's native memory. Itsfeedbackfiles are engineer corrections with a stated reason and itsprojectfiles are constraints not derivable from the code, which is the same contenttasks/lessons.mdexists to hold. A team that writes memories and never promotes them ends up with its real rules in one engineer's home directory.
When To Use
- The engineer asks to "share a personal lesson with the team"
- A personal lesson has recurred 3+ times and clearly applies to others
- The engineer says "promote", "share", "make this team-wide", "add this to lessons"
lesson-miningsurfaced a native-memory entry as a promotion candidate (rubric R7)
When NOT To Use
- Lesson is genuinely personal preference (style, individual workflow)
- Lesson is already in
tasks/lessons.md - Neither personal store exists or both are empty (nothing to promote)
- The memory is
type: user(a fact about the engineer) ortype: reference(a pointer to an external resource) — neither is a team lesson
Workflow
- Locate the candidate sources. Resolve to main worktree if in a worktree. There are two, and both are personal-scoped stores holding team-worthy rules:
.claude/lessons/personal.md— MTK's own gitignored personal store.${CLAUDE_CONFIG_DIR:-~/.claude}/projects/<sanitized-cwd>/memory/— Claude Code's native memory, where<sanitized-cwd>is the project working directory with/replaced by-(the same segment the session transcripts live under). The project segment is the parent ofmemory/: there is no top-level~/.claude/memory/, and looking there returns "no memories" however many exist. Files withmetadata.type: feedbackorprojectare the promotable ones;userandreferencememories are about the engineer or point at external resources and are almost never team lessons.
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.
- yesterday Changed d40f2a5781b6
- 9d ago First seen · 121 lines · 42 tokens per session scan A 314ae66d41e1
promote-lesson is a skill published in the GitHub repository moberghr/mtk-agent-toolkit (7 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 2,473 once invoked, about $0.0002 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
media-ingest
Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.
mem0-oss-to-platform
Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
memory
Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.