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.
git clone --depth 1 https://github.com/NovasPlace/CSMWrote 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/novasplace/csm/csm-recall)<a href="https://agentmods.dev/commands/novasplace/csm/csm-recall"><img src="https://agentmods.dev/badge/commands/novasplace/csm/csm-recall/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/commands/novasplace/csm/csm-recall"><img src="https://agentmods.dev/badge/commands/novasplace/csm/csm-recall.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 | $0.00012 | $0.00222 |
| Opus 5 | $0.00006 | $0.00111 |
| Sonnet 5 | $0.00002 | $0.00044 |
| Haiku 4.5 | $0.00001 | $0.00022 |
Grade A, and why
csm-recall 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 9d 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
Recall relevant Cross-Session Memory for: $ARGUMENTS
- Resolve
projectRootto the absolute root of the current workspace and keep every call scoped to it. - Call
csm_memory_searchwith the topic above (or the current task if no argument was given). - If results are thin, widen with
csm_memory_contextandcsm_memory_related; pull reusable lessons withrecall_lessons. - Verify every recalled claim against the current files, tests, and user instructions before acting on it — the workspace is the source of truth, not memory.
- Summarize only the evidence that changes what we do next. Do not dump raw records.
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.
- 9d ago First seen · 14 lines · 12 tokens per session scan A c48dded8f62a
csm-recall is a command published in the GitHub repository NovasPlace/CSM (42 stars, last pushed 2d ago), licensed MIT. It adds 12 tokens to every session and 222 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 2026-08-30.
Other commands, from other repositories
sessions
Manage Gemini Code session history, aliases, and session metadata.
compress
Save this Claude Code session to the vault and update the semantic memory index.
checkpoint
Save a mid-session checkpoint — for continuity between sessions of the same day.
resume
Load context from the vault before starting work.
preserve
Scan this conversation and silently save anything worth permanent memory.
memory-evolve
Phase 3.4 self-evolving memory. Convert reuse + routing-miss signals into PR-ready proposals (skill drafts + routing-rule additions). Never auto-applies.