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 sixb-ai/sixb --skill sixb-memorygit clone --depth 1 https://github.com/sixb-ai/sixbWrote 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/sixb-ai/sixb/sixb-memory)<a href="https://agentmods.dev/skills/sixb-ai/sixb/sixb-memory"><img src="https://agentmods.dev/badge/skills/sixb-ai/sixb/sixb-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/sixb-ai/sixb/sixb-memory"><img src="https://agentmods.dev/badge/skills/sixb-ai/sixb/sixb-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 | $0.00019 | $0.00797 |
| Opus 5.5 | $0.00008 | $0.00319 |
| Sonnet 5.5 | $0.00004 | $0.00159 |
| Haiku 4.5 | $0.00002 | $0.00080 |
Grade A, and why
sixb-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 yesterday.
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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory
The memory is a folder of Markdown files under $SIXB_MEMORY_DIR/<repo>/. Later conversations
start from its MEMORY.md and open the other files when a topic comes up.
user/is this user's own memory: only their conversations read it.project/is built up from every user's conversations, and everyone who uses the agent in this project reads it, including people who cannot see the data this user sees. Put in it what holds for everyone, such as the team's vocabulary, a convention, or how something is measured, and only what users told you: nothing about a particular person, and nothing learned from records or data.
Topic files
MEMORY.md is a list of one-line entries that every conversation reads. When a subject outgrows a
line or two, move it into a topic file with one subject, such as projects/payments.md or
team_structure.md, and leave one entry in MEMORY.md that links it with a few words on what it
holds.
Link a file with [[path]], from the repo root, leaving out .md: [[projects/payments]]. Other
files keep their extension: [[metrics/keep_rate.sql]].
# Memory
- Prefers summaries as short bullet lists (added 2026-10-04)
- Report invoice amounts excluding VAT (added 2026-10-21)
- Billing projects and how invoices are measured: [[projects/payments]] (added 2026-10-12)
- The query behind the weekly keep rate: [[metrics/keep_rate.sql]] (added 2026-10-15)
Writing an entry
- One bullet on one line, ending with the date it was added:
(added YYYY-MM-DD). - Write it so a conversation that never saw this one understands it.
- Edit in place. When the user corrects an entry, change or remove it; never leave two entries that disagree.
- Save how to find project data, such as the object type, the query or the property, never the data itself: the memory outlives the user's access to it.
Saving
End every edit with the save of the repo you edited, in the same command:
echo '- Report invoice amounts excluding VAT (added 2026-10-21)' >> "$SIXB_MEMORY_DIR/user/MEMORY.md" && sixb memory save user -m "Invoice amounts excluding VAT"
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.
- yesterday First seen · 69 lines · 19 tokens per session scan A 084dc53a2b4f
sixb-memory is a skill published in the GitHub repository sixb-ai/sixb (125 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 797 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 2026-10-24.
Other skills, from other repositories
knowledge_store_skill
Skill for working with local .knowledge.yaml files via KnowledgeStore. Use this when you need to recall, search, or manage directory-local memories and knowledge links stored in plain YAML alongside the user's project files. KnowledgeStore is directory-scoped. Each directory that contains a .knowledge.yaml file…
cocoscout
Relevance-ranked context loading — Tier 2 async subagent (Haiku, <5s) that fires after Tier 1 deterministic checks in UserPromptSubmit. Injects ranked context from CocoGrove, CocoContext, Environment Inspector, Prompt Studio, and CocoDream.
pod-checkpoint
Write a structured recovery snapshot to lifecycle/checkpoint.md before context reset — captures phase, stage, decisions, and pending items so $pod resume can restore precise context.
memory-fabric
Memory retrieval internals: knowledge graph orchestration with entity extraction, natural language query parsing, deduplication (>85% similarity), and cross-reference boosting over unified recency, relevance, and authority ranking. Use when designing or debugging how memory search itself works. Everyday lookups belong…
cocohealth
Context utilization monitor — background monitor that samples context window utilization via PostToolUse hook, surfaces advisory at 60% and critical warning with recovery decision matrix at 70%.
remember
Write-side memory: stores decisions, patterns, and outcomes in the MCP memory knowledge graph as entities with typed observations and relations. Use when something worth persisting across sessions was just learned or decided. To search or read existing memory, invoke memory; to debug retrieval internals…