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/principle-labs/corivo/savegit clone --depth 1 https://github.com/Principle-Labs/CorivoWrote 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/principle-labs/corivo/save)<a href="https://agentmods.dev/commands/principle-labs/corivo/save"><img src="https://agentmods.dev/badge/commands/principle-labs/corivo/save.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 | $0.00011 | $0.00302 |
| Opus 5 | $0.00005 | $0.00151 |
| Sonnet 5 | $0.00002 | $0.00060 |
| Haiku 4.5 | $0.00001 | $0.00030 |
Grade A, and why
save 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
Corivo Save
Record durable user or project memory into Corivo.
Preflight
- Verify
corivois available. - Verify the database is initialized with
corivo status. - Restate what will be saved and propose the annotation before executing.
- If the content looks temporary or sensitive in a risky way, pause and ask before saving.
Plan
- Classify the memory as
事实,知识,决策, or指令. - Choose a domain such as
self,people,project,asset, orknowledge. - Save the memory with
corivo save. - Confirm the save result back to the user.
Commands
corivo status
corivo save --content "<content>" --annotation "<nature> · <domain> · <tag>"
Verification
- Confirm the save command exits successfully.
- If possible, run a targeted
corivo queryto confirm the memory can be recalled. - Report the stored annotation and a brief summary, not the full raw shell output.
Summary
Present:
- What was saved
- Which annotation was used
- Whether verification succeeded
Next Steps
- Suggest
/corivo:querywhen the user wants to reuse this memory later. - Suggest refining the annotation if the saved memory is too broad.
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 · 48 lines · 11 tokens per session scan A 917f72e9a649
save is a command published in the GitHub repository Principle-Labs/Corivo (5 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 302 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
memory-forget
Command "memory-forget" from waittim/MemoryCustodian, covering memory-forget and review the preview, then apply its plan id.
speckit.archive
Archive a feature specification into main project memory after merge, resolving gaps and conflicts.
memory-compact
Run a dry run first.
mind
Claude Mind - Manage Claude's persistent memory stored in .claude/mind.mv2.
memory
Browse, search, and manage your saved technique library.
help
Show all available memex knowledge base commands.