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-beliefs)<a href="https://agentmods.dev/commands/novasplace/csm/csm-beliefs"><img src="https://agentmods.dev/badge/commands/novasplace/csm/csm-beliefs/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-beliefs"><img src="https://agentmods.dev/badge/commands/novasplace/csm/csm-beliefs.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 | $0.00013 | $0.00208 |
| Opus 5 | $0.00006 | $0.00104 |
| Sonnet 5 | $0.00003 | $0.00042 |
| Haiku 4.5 | $0.00001 | $0.00021 |
Grade A, and why
csm-beliefs 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 11d 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
Inspect CSM belief knowledge $ARGUMENTS.
- Resolve
projectRootto the current workspace root. - Call
csm_belief_knowledge(optionally filtered by the argument) andcsm_belief_scan_reportto show current beliefs and scan findings. - Use
csm_belief_promotion_scanto preview which beliefs are promotion-eligible. - Only call
csm_belief_promote— a mutation — when the user explicitly asks to promote a belief. Prefer a dry run first when available.
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.
- 11d ago First seen · 13 lines · 13 tokens per session scan A f472196342a1
csm-beliefs is a command published in the GitHub repository NovasPlace/CSM (42 stars, last pushed 3d ago), licensed MIT. It adds 13 tokens to every session and 208 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.
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.
lessons
Load, view, and save project lessons from tasks/lessons.md. Works on ALL platforms — Claude Code, Windsurf, Cursor, Codex, Antigravity, OpenCode.
instinct-export
Export instincts from project/global scope to a file.
memory
Manage local Kodelyth Memory — recall, capture, review, and curate what your AI knows about you.
security-audit
Parallel security audit — fires security-reviewer + dependency-doctor + api-guardian simultaneously. Full threat surface in one command.