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 arlinamid/centered-agent-memory --skill agent-memorygit clone --depth 1 https://github.com/arlinamid/centered-agent-memoryWrote 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/arlinamid/centered-agent-memory/agent-memory)<a href="https://agentmods.dev/skills/arlinamid/centered-agent-memory/agent-memory"><img src="https://agentmods.dev/badge/skills/arlinamid/centered-agent-memory/agent-memory/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/arlinamid/centered-agent-memory/agent-memory"><img src="https://agentmods.dev/badge/skills/arlinamid/centered-agent-memory/agent-memory.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 | $0.00093 | $0.01034 |
| Opus 5.5 | $0.00037 | $0.00414 |
| Sonnet 5.5 | $0.00019 | $0.00207 |
| Haiku 4.5 | $0.00009 | $0.00103 |
Grade A, and why
agent-memory 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 23d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Recalling earlier conversations
The cam index holds the conversations the user had with their other AI
tools — Claude Code, Claude Desktop / Cowork, Codex, Cursor, Gemini CLI,
Antigravity and Devin — so it can answer what this conversation cannot see:
what was decided, tried or fixed elsewhere. It only reads those tools' stores
and never changes them.
When to use it
Look before you ask or assume. When you start on a project you do not know, when the user refers to earlier work as if you had been there ("as we discussed", "what we did with Codex"), or when you need the reason for a decision the code does not explain, the answer may already be in the index. It knows the past, not the current workspace: what the open files or the repository say, read there.
For a project's history, start with cam_dossier: one call gives the tools,
dates and topics, and a cam_recall aimed by it finds more than several blind
ones. Project keys come from folder names and may differ from what the user
calls the project; cam_projects lists them.
cam_memory returns what earlier searches kept bringing up — a trail of what
mattered repeatedly, not a summary of the project.
cam_docs searches the files of indexed projects, including ones that are not
open here. Use it to find where something lives when you do not know where to
look, not in place of reading the workspace. The notes on its hits are the
user's own statements of what a project, folder or file is for. When you learn
something a note should say, propose it with the path and the sentence, and
let the user add it — every later agent will read a note as the user's word.
Reading the answers
Every hit carries a project-attribution confidence. strong comes from the
session's working directory or the paths it mentions; medium and weak come
from overlapping edit times and can be wrong, so when you cite one, say that it
belongs to the project by time overlap. weak hits are left out unless asked
for.
The index re-reads each source at query time. A hit marked stale (the source
changed since) or missing (it is gone) is passed on with that marking.
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.
- 23d ago Changed · -61 lines · +18 tokens per session fac5c378e3f9
- 1mo ago Changed · +47 lines b19254661f31
- 1mo ago First seen · 104 lines · 75 tokens per session scan A 168a29959c2b
agent-memory is a skill published in the GitHub repository arlinamid/centered-agent-memory (2 stars, last pushed 24d ago), licensed MIT. It adds 93 tokens to every session and 1,034 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
memory
Persist and retrieve agent memory across sessions — recall via the three-stage protocol (structure route → semantic search → navigation fallback), read via memoryload, see the wiki structure via memorybrowse, write well-placed pages via memorywrite (including section-level append/rewrite), maintain via memorycurate.…
memory-dream
Curate the workspace memory wiki as its appointed orchestrator. Trigger on a Cloud-scheduled Dream task or a user's direct curation request. Inspect candidates for orphan leaves, near-duplicates, stale pages, remote conflicts and oversized hubs; browse the graph, cluster leaves into INDEX/hub/leaf structure, maintain…
memory-import
Bulk-import an external knowledge base into Prismer memory via the three-layer import pipeline (07 §3.1). Use when the user asks to import/migrate documents, a knowledge base, or notes into workspace memory. Layer 1 lands raw documents (zero LLM, instantly searchable); Layer 2 is YOUR distillation work — you read the…
brain-page
Operating manual for reading and writing a project's brain — every read and write goes through the bundled zero-dependency brain CLI; never hand-edit brain files. Read it before creating or modifying any page or root page.
brain-setup
Bootstrap the Open Project Brain Standard into the current project — prefer brain init (ensure BRAIN.md, scaffold empty brain brainRoot-aware, default-wire CLAUDE.md + AGENTS.md). Optionally install a pre-commit hook and a Claude Code or Codex SessionStart hook.
mnemon
Persistent memory CLI for LLM agents. Store facts, recall past knowledge, link related memories, manage lifecycle.