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 albedoweb/agmem --skill setupgit clone --depth 1 https://github.com/albedoweb/agmemWrote 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/albedoweb/agmem/setup)<a href="https://agentmods.dev/skills/albedoweb/agmem/setup"><img src="https://agentmods.dev/badge/skills/albedoweb/agmem/setup/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/albedoweb/agmem/setup"><img src="https://agentmods.dev/badge/skills/albedoweb/agmem/setup.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 | $0.00024 | $0.00349 |
| Opus 5.5 | $0.00010 | $0.00140 |
| Sonnet 5.5 | $0.00005 | $0.00070 |
| Haiku 4.5 | $0.00002 | $0.00035 |
Grade A, and why
setup 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 3d 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
Set up agmem
Work in the target repository. Check for agmem first. If absent, install
from the project source using an available isolated installer:
uv tool install --from git+https://github.com/albedoweb/agmem agmem
Alternatively use pipx install git+https://github.com/albedoweb/agmem.
The project needs Python 3.12 or newer; with uv, add --python 3.12 if needed.
For development in a local agmem checkout, uv tool install --editable .
uses that checkout. Never install the unrelated PyPI package named agmem.
Inspect the repository's ignore rules and private/untracked notes before
indexing. The indexer respects the root .gitignore but can include untracked
files. Exclude private material before generating an index intended for sharing.
agmem init
agmem index
agmem context '<identifiers from this repository>' -n 4
Inspect the resulting source references and verify that the sample query points
to real code. Explain where .agmem/ lives and how to refresh it.
This Codex plugin provides skills; it does not install background hooks or a watcher. Install Git hooks only when requested. Enable a shared index only when the user requests it; preserve the repository's default ignore policy otherwise. If Codex is running in a linked worktree, explain that agmem currently resolves memory to the main checkout before initializing or updating it.
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.
- 3d ago First seen · 38 lines · 24 tokens per session scan A 1f0bf64cc308
setup is a skill published in the GitHub repository albedoweb/agmem (2 stars, last pushed 3d ago), licensed Apache-2.0. It adds 24 tokens to every session and 349 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-26.
Other skills, from other repositories
aimh-intake
A front-door routing skill for HMA, a long-term memory system. It first identifies what a submitted text or file is, then sends it to the matching storage workflow.
aimh-ingest
A workflow for saving text, notes, logs, articles, reference material, ideas, and conversations into HMA, a long-term memory system for agents.
aimh-recall
A memory lookup helper that searches long-term memory when a person, project, object, date, or topic is mentioned in conversation.
aimh-always
A long-term memory system for an AI assistant, called Hybrid Memory Architecture. After it is activated with its command, it stays active in the conversation and can store or retrieve persistent facts, decisions, preferences, and past problems.
oc-dossier
A system for storing and recalling original characters, such as fictional people created for stories. It can build character records from text or files and retrieve them later for role-play.
aimh-daylog-archive
A daylog system for AIMH where the daylog is the authoritative stream of events, such as decisions, changes, problems, and discussions. Topic views and indexes are derived from markers in those entries.