share

share is a skill for Claude Code from rhoulihan/mneme. It costs 45 tokens per session (765 once invoked), scanned A, original, Apache-2.0.

A human approval process for selecting stored knowledge candidates and applying approved ones to knowledge-plugin branches. Approved changes may be pushed as a pull request.

In plain words
What is it for?
Use it to inspect candidate changes, compare possible duplicates, reject entries with reasons, approve selected entries, and decide whether to create a pull request.
Why use it?
It keeps unapproved, duplicate, cross-boundary, or secret-containing knowledge from being added automatically.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the mneme plugin — 11 skills, 3 hooks shipped together

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add rhoulihan/mneme
Claude Code
/plugin install mneme

Made for: Claude Code.

Or install mneme, the plugin that ships this one along with the rest of its 11 skills, 3 hooks.

Wrote 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.

agentmods badge for share

README.md
[![agentmods](https://agentmods.dev/badge/skills/rhoulihan/mneme/share.svg)](https://agentmods.dev/skills/rhoulihan/mneme/share)
Your own site
<a href="https://agentmods.dev/skills/rhoulihan/mneme/share"><img src="https://agentmods.dev/badge/skills/rhoulihan/mneme/share.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 765 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00045 $0.00765
Opus 5 $0.00023 $0.00382
Sonnet 5 $0.00009 $0.00153
Haiku 4.5 $0.00005 $0.00076

Measured 5d ago against content hash f631e7d0e0cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

share 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 5d 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.

skills/share/SKILL.md · 17 lines

What it actually says

You are driving mneme's harvest gate. The CLI (binary at "$CLAUDE_PLUGIN_ROOT/bin/mneme" when installed, else bin/mneme) does all mechanical work — never edit knowledge repos, staging files, or git state directly.

  1. Run mneme share list and present the queue grouped by target plugin: id, type/edit, confidence, and every annotation. Call out [boundary] flags (candidate routed toward a less-restricted repo — the user must explicitly confirm those) and [similar: <unit>] flags (possible duplicate of existing knowledge — suggest comparing before approving). [QUARANTINED] candidates (visible with --all) contain secret-scan hits and CANNOT be applied; they need redaction first.
  2. For each candidate the user wants to inspect, run mneme share diff <id> and show the content (new units whole, updates as diffs).
  3. Collect decisions conversationally. Rejections: run mneme decline <id> --reason "<their reason>" — the reason matters; the distiller uses the ledger to never re-propose it.
  4. Approvals: run mneme share apply --ids <id1>,<id2>,... (add --no-push if the user wants the branch left local this time). Report each result line and any PR URL verbatim. If the target repo still carries a legacy top-level facts/ directory, the harvest migrates it onto the same branch — so the pull request shows those moves alongside the approved units, no user action is required, and mneme migrate exists for a repo with nothing else pending.
  5. Mneme never writes a knowledge repo's main. Approved units always land on a mneme/harvest-* branch: with a remote, mneme pushes that branch and opens the PR; without one, the branch stays local and the pr: line says so. In the no-remote case, offer to merge it or add a remote and push — and do that only WITH the user's explicit go-ahead, in their repo, with plain git.
  6. If a candidate is routed to the wrong plugin, do not apply it — re-route it: mneme share route <id> --target <plugin> (use --target unassigned to un-route one you cannot place yet). Say what changed: the candidate id is DERIVED from the target, so routing re-mints it, and the command prints both. Never reach for decline instead — a decline is a permanent verdict, and for a candidate with no destination it is recorded GLOBALLY, so declining an unrouted candidate silences that knowledge for every repo rather than just the wrong one. Route refuses on its own terms and each refusal names the fix: a body already declined for the destination, the same knowledge already staged there, an unregistered target, or a move into a less-restricted repo — that last one needs the user's explicit go-ahead and --allow-boundary. Routing never clears a [QUARANTINED] flag. A route also STICKS: mneme records the destination you moved it off, so the next distill run does not propose the same sentence for the wrong repo again — routing it back clears that record, because you changed your mind.

Never apply candidates the user has not explicitly approved in this conversation.

Changes

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.

  1. 5d ago First seen · 17 lines · 45 tokens per session scan A f631e7d0e0cf

Subscribe to this mod's changes

share is a skill published in the GitHub repository rhoulihan/mneme (6 stars, last pushed 12d ago), licensed Apache-2.0. It adds 45 tokens to every session and 765 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens