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/novasplace/csm/csm-selfmodelgit 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-selfmodel)<a href="https://agentmods.dev/commands/novasplace/csm/csm-selfmodel"><img src="https://agentmods.dev/badge/commands/novasplace/csm/csm-selfmodel.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 | $0.00134 |
| Opus 5 | $0.00005 | $0.00067 |
| Sonnet 5 | $0.00002 | $0.00027 |
| Haiku 4.5 | $0.00001 | $0.00013 |
Grade A, and why
csm-selfmodel 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 5d 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
Show the CSM self-model $ARGUMENTS.
- Resolve
projectRootto the current workspace root. - Call
csm_self_modelfor the authoritative live capability state, andcsm_living_state_previewfor the current living-state snapshot. - Summarize capabilities, their status/provenance, and anything that looks stale or contradicted by the current workspace.
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.
- 5d ago First seen · 12 lines · 11 tokens per session scan A f3c69096c406
csm-selfmodel is a command published in the GitHub repository NovasPlace/CSM (42 stars, last pushed yesterday), licensed MIT. It adds 11 tokens to every session and 134 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
commit-all
Group all changes semantically and commit each group separately.
hatch3r-benchmark
Run and analyze performance benchmarks. Compare results against baselines, identify regressions, and produce performance reports.
evolve
Analyze instincts and suggest or generate evolved structures.
hatch3r-refactor-plan
Plan a refactoring or migration effort -- spawn parallel researchers, produce refactoring spec, ADR(s), and phased todo.md entries for board-fill.
promote
Promote project-scoped instincts to global scope.
terse
Switch reply compression level — /terse [lite|full|ultra|off]. Complements RTK (input savings) with output-side savings.