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 ahkedia/lyra-ai --skill remembergit clone --depth 1 https://github.com/ahkedia/lyra-aiWrote 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/ahkedia/lyra-ai/remember)<a href="https://agentmods.dev/skills/ahkedia/lyra-ai/remember"><img src="https://agentmods.dev/badge/skills/ahkedia/lyra-ai/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/ahkedia/lyra-ai/remember"><img src="https://agentmods.dev/badge/skills/ahkedia/lyra-ai/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 | $0.00704 |
| Opus 5.5 | $0.00013 | $0.00282 |
| Sonnet 5.5 | $0.00006 | $0.00141 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
remember scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Remember
Saves meaningful context from the current conversation into ByteRover's long-term memory (.brv/context-tree/). Useful after technical decisions, project planning sessions, debugging sessions, or any conversation worth recalling later.
When to Use
- After discussing a project decision (e.g., "we decided to use X because Y")
- After a technical deep-dive (architecture, debugging session, config changes)
- When Akash asks: "remember this" or "save this"
- Self-invoke after completing a complex multi-step task — ask "Want me to remember this?" before curating
Operations
Curate current conversation context
TIMESTAMP=$(date +%s)
TMPFILE="/tmp/lyra-memory-${TIMESTAMP}.md"
# Write a structured summary of what's worth remembering
cat > "$TMPFILE" << 'SUMMARY'
[SUMMARY_CONTENT]
SUMMARY
brv curate "$TMPFILE"
rm -f "$TMPFILE"
Decision Logic
- Identify what's worth remembering: decisions made, facts learned, preferences expressed, project context, technical outcomes
- Skip: greetings, trivial acknowledgments, transient task outputs (e.g., "what's on my shopping list")
- Write a structured summary covering:
- What was decided or done (concrete outcome)
- Why (reasoning, if stated)
- Key details (commands, file paths, config changes, names)
- What to remember for next time (carry-forward context)
- Run
brv curateon the temp file - Report what was saved in one sentence
Examples
User says: "/remember"
Action: Summarize the conversation, write to /tmp/lyra-memory-{ts}.md, run brv curate, clean up
Response: "Saved to memory: ByteRover installed on Lyra, Context Tree bootstrapped from MEMORY.md and SOUL.md, /remember skill created."
User says: "remember that we use paise not rupees in Reap Capital" Action: Write a targeted fact-note, curate it Response: "Saved to memory: Reap Capital uses paise (not rupees) for all monetary values."
User says: "save the decisions from this session" Action: Same as /remember — summarize the session's key decisions and curate them Response: One-sentence summary of what was saved.
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.
- 1mo ago First seen · 71 lines · 32 tokens per session scan A 31dfeefae20c
remember is a skill published in the GitHub repository ahkedia/lyra-ai (5 stars, last pushed 1mo ago), licensed MIT. It adds 32 tokens to every session and 704 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
autograph
Schema-as-code enforcement for any Obsidian vault. Zero hardcoded domains. Use when creating vault cards, checking vault health, running schema compliance, deduplicating entities, generating MOC indexes, running decay cycles, bootstrapping a vault, fixing wikilinks, finding orphans or backlinks, extracting entities…
dbrain-processor
Personal assistant for processing daily voice/text entries from Telegram. Classifies content, saves thoughts to Obsidian with wiki-links, generates HTML reports. Integrates Your Business context (clients, projects, CRM). Triggers on /process command or daily 21:00 cron.
db-maintenance
A maintenance guide for a SQLite database that stores memories, sessions, and conversation records in one file. SQLite is a database system that can keep data in a single file.
memory-tidy
A memory-maintenance skill for finding duplicate, expired, or overly long entries in an assistant's memory index. It suggests changes for a person to approve and archives entries instead of permanently deleting them.
feedback-capture
A feedback-memory skill that turns clear user corrections or confirmations about an answer into a short reusable instruction. It ignores ordinary thanks and records ambiguous reactions without guessing their meaning.
mem0-vercel-ai-sdk
Mem0 provider for Vercel AI SDK (@mem0/vercel-ai-provider). TRIGGER when: user mentions "vercel ai sdk", "@mem0/vercel-ai-provider", "createMem0", "retrieveMemories", "addMemories", "getMemories", "searchMemories", "mem0 vercel", "AI SDK provider", "AI SDK memory", or is using generateText/streamText with mem0. Also…