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.
/plugin marketplace add rhoulihan/mneme/plugin install mnemeWrote 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/rhoulihan/mneme/adopt)<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>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 | $0.00071 | $0.00792 |
| Opus 5 | $0.00036 | $0.00396 |
| Sonnet 5 | $0.00014 | $0.00158 |
| Haiku 4.5 | $0.00007 | $0.00079 |
Grade A, and why
adopt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
The binary is "$CLAUDE_PLUGIN_ROOT/bin/mneme" when installed, else bin/mneme.
-
If the repo is not yet registered, register it first:
mneme registry add <name> --repo <url> --clone(or--pathfor an existing checkout). -
Read what the repo already says about itself:
mneme adopt $ARGUMENTS --describeprints 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. -
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.
-
Say where the scope ends. When
siblingsis non-empty, state which kinds of knowledge go to each sibling instead ("you already haveteam-kbcovering 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. -
Apply the agreed scope:
mneme adopt $ARGUMENTS --description "<the agreed scope>" --owner "<their team>". -
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 ownskills/orCONTRIBUTING.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:shareand/mneme:reviewwork exactly as they do anywhere.
Override the classification with
--as-pluginor--plainif the user wants the other one. - plugin — the repo is, or is becoming, a knowledge plugin. Full scaffold: manifests,
-
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.
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.
- 6d ago First seen · 27 lines · 71 tokens per session scan A 395ef40d762d
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.
Other skills, from other repositories
syncing-memory-filesystem
Diagnose and repair MemFS repository setup, remote sync, authentication failures, optional backup remotes, or merge/rebase conflicts. Do not load for routine memory reads or edits.
git-ai-search
Search and restore AI conversation context from git history.
github-ops
GitHub CLI for issues, PRs, code search, CI logs, releases, and API queries. Requires gh CLI and auth.
mulch-record-from-evidence
Turn the evidence of a finished work session — git commits, changed files, recently-touched seeds issues — into well-formed ml record invocations. Use at session close, when an agent has made changes worth preserving as mulch expertise but hasn't yet recorded them.
release-finalizer
Merges a release PR, associates it with resolved issues, replies to issue reporters, and closes issues. Use after PR review is complete and ready for merge. Closes the release cycle.
release-prep
Orchestrates the full release preparation flow for a plugin — version sync across 7+ files, bilingual release notes creation, and commit message drafting. Use before submitting a PR. Does NOT push or create a PR; that is handled by pr-submitter.