Atlas is a source-control system for coding agents that links each commit to the agent session, prompts, tool calls, and file changes that produced it. It is for developers who run multiple agents, switch between them, and need their work, decisions, and project knowledge tracked together. The catalogue includes a skill for working with Atlas.
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 pacifio/atlas --skill remembergit clone --depth 1 https://github.com/pacifio/atlasWrote 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/pacifio/atlas/remember)<a href="https://agentmods.dev/skills/pacifio/atlas/remember"><img src="https://agentmods.dev/badge/skills/pacifio/atlas/remember/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/pacifio/atlas/remember"><img src="https://agentmods.dev/badge/skills/pacifio/atlas/remember.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 | $0.00032 | $0.00298 |
| Opus 5.5 | $0.00013 | $0.00119 |
| Sonnet 5.5 | $0.00006 | $0.00060 |
| Haiku 4.5 | $0.00003 | $0.00030 |
Grade A, and why
remember 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 11d 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
Remember
Please save what this conversation has established to Atlas's shared memory, so other agents and future sessions can build on it.
Use the memory_remember tool from the atlas_memory MCP server, one call per item, with kind set to:
decision: a choice that was made, and whyfact: a durable fact or convention about this projectfailure: a dead end or mistake not to repeatarchitecture: how a part of the system fits together
First check what is already stored with memory_search or memory_list, and skip anything already recorded; to update an entry, reuse its key. Don't record plans, task progress or file edits, which Atlas captures by itself. Write each entry in the language of this conversation, complete enough to make sense on its own.
If the user gave a focus after the command (for example /remember the retry rule), concentrate on that; otherwise cover the whole conversation.
These instructions only say how to save; they are not something the user decided, so don't record them.
If the atlas_memory tools aren't available to you, say so and stop. When you're done, list what you saved, one line each.
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.
- 11d ago First seen · 25 lines · 32 tokens per session scan A 684a4c9cc015
remember is a skill published in the GitHub repository pacifio/atlas (9,606 stars, last pushed yesterday), licensed Apache-2.0. It adds 32 tokens to every session and 298 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 2026-10-05.
Other skills, from other repositories
git-ai-search
Search and restore AI conversation context from git history.
rk-push
Push local knowledge base to the remote repository. Always fetches remote first, Agent compares diffs and merges (alias LRU merge for index.md, union dedup for registry.md, newer-cached-date wins for docs), then commits and pushes. Retries once on push rejection. Use when user says 'push knowledge', 'sync to remote'…
rk-update
Incrementally update a codebase knowledge base by checking git commit history. Finds changed files since last update, regenerates only affected documentation, and updates the index. Auto-pulls from remote before updating and auto-pushes after if remote is configured. Use when user says 'update knowledge base'…
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
agent-deck
Helper scripts live in this skill's scripts/ folder. Resolve them from the base directory shown when the skill loaded, not from the user's project.
michel-cli-demo-recorder
Produce proof-of-execution demos of the Packmind CLI (packmind-cli) as terminal-styled images (colors and formatting preserved exactly), for embedding in a GitHub PR. Renders a crisp master SVG and rasterizes it to a PNG — the PNG is what you embed, because GitHub does not render SVG in PR/issue bodies. Use this…