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 clawsouls/clawsouls-claude-code-plugin --skill swarm-memorygit clone --depth 1 https://github.com/clawsouls/clawsouls-claude-code-pluginWrote 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/clawsouls/clawsouls-claude-code-plugin/swarm-memory)<a href="https://agentmods.dev/skills/clawsouls/clawsouls-claude-code-plugin/swarm-memory"><img src="https://agentmods.dev/badge/skills/clawsouls/clawsouls-claude-code-plugin/swarm-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/clawsouls/clawsouls-claude-code-plugin/swarm-memory"><img src="https://agentmods.dev/badge/skills/clawsouls/clawsouls-claude-code-plugin/swarm-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 | $0.00029 | $0.00312 |
| Opus 5.5 | $0.00012 | $0.00125 |
| Sonnet 5.5 | $0.00006 | $0.00062 |
| Haiku 4.5 | $0.00003 | $0.00031 |
Grade A, and why
swarm-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 2mo 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
Swarm Memory — Git-Based Memory Sync
Manage structured memory files that persist across sessions and sync across devices via Git.
When to activate
- User asks about agent memory, knowledge, or recall
- User mentions MEMORY.md, memory files, or daily logs
- User wants to sync, search, or organize agent memories
- Memory conflicts or merge issues arise
Memory architecture (4-Tier)
- T0 (Identity): SOUL.md, IDENTITY.md — immutable core
- T1 (Long-term): MEMORY.md — curated, promoted from T2
- T2 (Short-term): memory/*.md — daily logs, topic files
- T3 (Session): Current conversation context
Operations
- Search: Grep across all memory files for relevant context
- Sync: Git add/commit/push memory files to remote
- Compact: Summarize old entries, promote to MEMORY.md
- Resolve: Handle merge conflicts in memory files (prefer newer + human edits)
Best practices
- Topic files:
memory/topic-*.md(max 30 lines history, 50 lines decisions) - Daily logs:
memory/YYYY-MM-DD.md - Always commit memory changes with descriptive messages
- Search memory before answering questions about prior work
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.
- 2mo ago First seen · 33 lines · 29 tokens per session scan A caa2550a8b44
swarm-memory is a skill published in the GitHub repository clawsouls/clawsouls-claude-code-plugin (2 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 29 tokens to every session and 312 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 2026-08-31.
Other skills, from other repositories
GitLearn
Mines durable LTM memories from past git commits through the git-learner agent (no API key needed). Use when the user says 'learn from our git history', 'mine the last N commits', 'backfill memories since ', 'onboard this repo into LTM', or wants to harvest patterns after a sprint.
git-ai-search
Search and restore AI conversation context from git history.
flow-next-land
Resolve feedback and CI for one named pull request, then merge when authorized and ready. Emits LANDVERDICT. Use when asked to land a pull request.
flow-next-worktree-kit
Manage git worktrees (create/list/switch/cleanup) and copy .env files. Use for parallel feature work, isolated review, clean workspace, or when user mentions worktrees.
pr
Comprehensive PR/issue review - analyzes architecture, tests, identifies unrelated changes mixed in, drafts review comment or issue comment. Use when user asks to review a PR, check a PR, look at PR changes, or comment on an issue.
re0-git
Rewrite a finished commit's message into a clean, handoff-ready form in your own log style, so git log alone tells the story. User-invoked: run it after a commit.