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 LucasSantana-Dev/sharekit --skill memory-promotegit clone --depth 1 https://github.com/LucasSantana-Dev/sharekitWrote 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/lucassantana-dev/sharekit/memory-promote)<a href="https://agentmods.dev/skills/lucassantana-dev/sharekit/memory-promote"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/memory-promote/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/lucassantana-dev/sharekit/memory-promote"><img src="https://agentmods.dev/badge/skills/lucassantana-dev/sharekit/memory-promote.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 | $0.00074 | $0.00655 |
| Opus 5 | $0.00037 | $0.00328 |
| Sonnet 5 | $0.00015 | $0.00131 |
| Haiku 4.5 | $0.00007 | $0.00065 |
Grade A, and why
memory-promote 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 7d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory Promote
Extends cooperative-mode memory isolation from "never leak" to "curated
sharing". Personal memory stays private by default; sharing is an explicit,
reviewable act. Policy: .harness/memory-scopes.json (promotion requires
review; private tags never promote).
Flow
- Select. Identify the personal-scope note to promote
(
~/.claude/projects/<slug>/memory/or.agents/memory/personal/). If the user gave no path, list recent personal notes and let them pick. - Strip. Remove, in order:
<private>...</private>tagged spans entirely (never promoted, per policy)- secret-shaped strings (tokens, keys, emails, internal hostnames, personal
paths) — replace with a
[redacted: <kind>]placeholder - names of people not on the team, unless the user confirms
- Propose. Write the stripped note to a review artifact, never directly
to shared memory:
- target:
.agents/memory/proposals/<YYYY-MM-DD>-<slug>.md - include a header: source scope, author, date, what was stripped
- target:
- Review gate. Run
hooks/memory-scope-gate.shsemantics against the proposal: if any<private>tag or personal-scope path reference survives, stop and report — do not submit. Present the diff to the user for explicit approval. - Submit. Only after user approval: push the proposal through the team
vault —
bash scripts/team-memory-sync.sh push <proposal.md>(requires.harness/team-vault.json; the transport re-checks for<private>tags and refuses them). The note lands in the shared vault repo; teammates receive it on their nextteam-memory-sync.sh pull. If the team vault is a PR-governed repo, open the vault PR instead of a direct push. Record the promotion in the note header.
Hard rules
- Never write to team/org scope directly; the proposal artifact is the only path.
- Never promote
<private>-tagged content, even if the user asks — strip or refuse. - If
.harness/memory-scopes.jsonis absent, behave as solo: warn that no team scope is declared and stop after step 3. - Batch promotion (>5 notes) requires one approval per note, not a blanket yes.
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.
- 7d ago First seen · 56 lines · 74 tokens per session scan A 2e96cfef9efe
memory-promote is a skill published in the GitHub repository LucasSantana-Dev/sharekit (1 stars, last pushed 3d ago), licensed MIT. It adds 74 tokens to every session and 655 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
atlas-sync
Restore project context after clear/new session by following the canonical sync command doc.
neat-freak
Knowledge and governance closeout: reconcile project docs, rule files (CLAUDE.md/AGENTS.md), authorized agent memory, and workspace residue with what the code and runtime actually do, so the next session or the next person starts from one current answer. Trigger when the user names "neat-freak", "洁癖", or "/neat" — and…
learn
Diagnose and fix agent behavioral surfaces when the user corrects a mistake — connects to Claude native memory.
install
Install the Rekal binary on this machine. Use when rekal is not on PATH — a command reported command not found — or when the user asks to install Rekal. Once per machine, not per repository; to set up a repo that already has the binary, use the init skill instead.
memorywhale
Query and write durable debugging memory recorded by MemoryWhale. Use when debugging a failure that may have happened before, when you need the exact error/flags/output from an earlier attempt, when the user asks "how did we fix this last time?", or once you've figured out why something failed / how a fix worked and…
handoff
Use when work is changing sessions, agents, or machines and the next pass needs a compact handoff document with current state, open questions, and next steps instead of raw chat history.