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 agentmods add commands/joaoequer/oficina/lembrargit clone --depth 1 https://github.com/JoaoEquer/OficinaWrote 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/commands/joaoequer/oficina/lembrar)<a href="https://agentmods.dev/commands/joaoequer/oficina/lembrar"><img src="https://agentmods.dev/badge/commands/joaoequer/oficina/lembrar.svg" alt="Measured on agentmods" 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 | $0.00021 | $0.00197 |
| Opus 5 | $0.00010 | $0.00098 |
| Sonnet 5 | $0.00004 | $0.00039 |
| Haiku 4.5 | $0.00002 | $0.00020 |
Grade A, and why
lembrar 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 3d 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
Search past session memory for $ARGUMENTS.
- If
.oficina/memory/doesn't exist in this project, say so and stop — nothing to search yet (probably/oficina:fechar-sessaowas never run here). - Search
.oficina/memory/*.mdandOPEN_DECISIONS.md(if present) for $ARGUMENTS, case-insensitive. - For each match, show the file, the dated entry it belongs to, and the matching line(s) in context — quote directly, never paraphrase.
- If nothing matches, say so plainly. Do not guess or answer from general knowledge — this is memory recall, not free-form Q&A.
Keep the report terse: matches grouped by date, most recent first.
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.
- 3d ago First seen · 14 lines · 21 tokens per session scan A 37013da0f117
lembrar is a command published in the GitHub repository JoaoEquer/Oficina (2 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 197 once invoked, about $0.0001 per session on Opus 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 commands, from other repositories
memstack-search
Search MemStack memory for past sessions, insights, and project context.
memory-why
Show why a memory recall returned what it did -- BM25 vs vector vs hybrid provenance.
on
Turn rolling-context back on for this session (or --global for the whole machine) — active from the next request.
check
Run mneme check against a file or proposed change.
context
Retrieve relevant decisions from project memory for the current task.
code-review
Run parallel specialized review agents and produce aggregated quality report.