adopt

adopt is a skill for Claude Code from rhoulihan/mneme. It costs 71 tokens per session (792 once invoked), scanned A, original, Apache-2.0.

A guided way to add mneme knowledge management to an existing repository. A repository is a project folder tracked with version control; mneme keeps knowledge for an ordinary app or service in a separate mneme-index folder.

In plain words
What is it for?
Use it to inspect a repository’s README, manifests, files, language mix, commits, and existing agent documentation. It then drafts a scope statement for the user to approve before adoption.
Why use it?
It helps define what knowledge belongs in the repository before adding governance files. This gives later searches a clear scope instead of mixing unrelated procedures and facts.

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 adopt

README.md
[![agentmods](https://agentmods.dev/badge/skills/rhoulihan/mneme/adopt.svg)](https://agentmods.dev/skills/rhoulihan/mneme/adopt)
Your own site
<a href="https://agentmods.dev/skills/rhoulihan/mneme/adopt"><img src="https://agentmods.dev/badge/skills/rhoulihan/mneme/adopt.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 792 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 $0.00071 $0.00792
Opus 5 $0.00036 $0.00396
Sonnet 5 $0.00014 $0.00158
Haiku 4.5 $0.00007 $0.00079

Measured 6d ago against content hash 395ef40d762d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

adopt 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 6d 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/adopt/SKILL.md · 27 lines

What it actually says

The binary is "$CLAUDE_PLUGIN_ROOT/bin/mneme" when installed, else bin/mneme.

  1. If the repo is not yet registered, register it first: mneme registry add <name> --repo <url> --clone (or --path for an existing checkout).

  2. Read what the repo already says about itself: mneme adopt $ARGUMENTS --describe prints a JSON bundle — the README's first paragraph, package manifests, the top-level tree, the language mix, recent commit subjects, which agent-facing docs exist, the scopes already registered, and the mode adoption will pick. It reads and reports; it adopts nothing. Read all of it before you say anything to the user.

  3. Draft the scope statement, then ask. Do not ask the user to invent one cold — that is how vague scopes get written, and the scope statement is the routing prompt every candidate fact is matched against, so a vague one steals candidates from every sibling scope. Propose a statement built from the bundle, naming which source each claim came from, and describe what knowledge belongs here — the systems, failure modes and operational surfaces someone working in this repo learns the hard way. Not what the product is: a README is marketing, and marketing prose used as a routing prompt matches everything.

  4. Say where the scope ends. When siblings is non-empty, state which kinds of knowledge go to each sibling instead ("you already have team-kb covering the widget platform; a deploy gotcha specific to THIS service goes here, a platform-wide one goes there"). That boundary is the part the user can actually correct and the part they cannot supply unprompted. Then ask only what the bundle cannot answer: the exclusions, the sensitivity, and any boundary you could not settle yourself. Never re-ask something already in the bundle.

  5. Apply the agreed scope: mneme adopt $ARGUMENTS --description "<the agreed scope>" --owner "<their team>".

  6. Report what happened. The first line names the mode and why it was chosen:

    • plugin — the repo is, or is becoming, a knowledge plugin. Full scaffold: manifests, skills/knowledge-index/, repo-wide CODEOWNERS and CI.
    • plain — an ordinary app, service or infra repo. mneme keeps to mneme-index/ at the root and takes nothing else over: no plugin manifests, no claim on the repo's own skills/ or CONTRIBUTING.md, CODEOWNERS scoped to /mneme-index/, and CI (mneme-validate.yml) that only runs when the knowledge changes. Tell the user plainly what plain mode does NOT give them: no marketplace distribution, and no /mneme:classify — a plain repo has no destination skills to file facts into. /mneme:share and /mneme:review work exactly as they do anywhere.

    Override the classification with --as-plugin or --plain if the user wants the other one.

  7. Relay every note the command printed — a CODEOWNERS it found and deliberately left alone comes with the line to add by hand — surface any lint warning about existing content, and remind the user the changes are uncommitted: they review and commit through their repo's normal process.

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. 6d ago First seen · 27 lines · 71 tokens per session scan A 395ef40d762d

Subscribe to this mod's changes

adopt is a skill published in the GitHub repository rhoulihan/mneme (6 stars, last pushed 12d ago), licensed Apache-2.0. It adds 71 tokens to every session and 792 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 2026-08-31.