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 skills add NovasPlace/CSM --skill csm-handoffgit 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/skills/novasplace/csm/csm-handoff)<a href="https://agentmods.dev/skills/novasplace/csm/csm-handoff"><img src="https://agentmods.dev/badge/skills/novasplace/csm/csm-handoff/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/skills/novasplace/csm/csm-handoff"><img src="https://agentmods.dev/badge/skills/novasplace/csm/csm-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00027 | $0.00248 |
| Opus 5 | $0.00014 | $0.00124 |
| Sonnet 5 | $0.00005 | $0.00050 |
| Haiku 4.5 | $0.00003 | $0.00025 |
Grade A, and why
csm-handoff 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 10d 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
CSM Handoff
Make every transition cheap to resume. Scope all calls to the current projectRoot.
When to hand off
- Before stopping, before an expected compaction, or before transferring work to another session or person.
- When context pressure is high — inspect
csm_context_pressurewhen a message snapshot is available.
Procedure
- Resolve
projectRootto the current workspace root. - If the current state is expensive to reconstruct,
create_checkpoint. Checklist_checkpointsto avoid redundant checkpoints. - Record the final durable milestone with
bridge_sync_turn, then callbridge_handoff_summary. - Write the handoff concretely: outcome, files changed, verification performed, open risks, and the single next action.
Safety
- Never persist secrets, credentials, tokens, or unnecessary sensitive content — redact first.
- State outcomes faithfully: if tests failed or a step was skipped, say so.
The csm-handoff-writer agent can perform this whole procedure autonomously.
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.
- 10d ago First seen · 28 lines · 27 tokens per session scan A bf12da5c3ed0
csm-handoff is a skill published in the GitHub repository NovasPlace/CSM (42 stars, last pushed 3d ago), licensed MIT. It adds 27 tokens to every session and 248 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 skills, from other repositories
dark-memory
Use for governance, memory, drift detection, and audit trail via dark-memory-mcp. Covers 52 canonical + 3 red-team tools across 16 namespaces: session lifecycle, agentmemory CRUD+search, vibe-flow spec/artifact publish + drift, LLM-as-judge, delegation+mindset, research, observability, error observatory, governance…
luo-hongxian-perspective
A Chinese-language interpretation framework based on the historical scholar Luo Hongxian and the Chinese astrology system Zi Wei Dou Shu.
zhang-zhongjing-perspective
A learning framework based on Zhang Zhongjing, a Chinese physician from the Eastern Han period, for reasoning about traditional Chinese medical diagnosis and treatment.
trading-manual-writer
A writing skill for creating sections of a trading manual for beginners and individual investors. It explains financial instruments or trading topics in Markdown and can include SVG illustrations.
find-postgres-bug
Find latent bugs in a local PostgreSQL source tree (RELxxSTABLE branch or HEAD) the way a core hacker does: build a heavily-poisoned debug instance (cassert + cache-discard + -O0/-ggdb3 + core dumps), fuzz it (sqlsmith) until the backend crashes, triage the core into a minimal reproducer (MRE), git-bisect the…
multi-expert-analyzer
A multi-field analysis workflow that assigns difficult questions to specialists, combines their findings, checks facts, and performs a second critical review. It produces a readable answer aimed at non-experts.