csm-continuity

csm-continuity is a skill for Codex from NovasPlace/CSM. It costs 60 tokens per session (681 once invoked), scanned A, original, MIT.

Instructions for using Cross-Session Memory, a system that preserves useful task context between coding sessions. It covers saved state, goals, checkpoints, handoffs, and context recovery.

In plain words
What is it for?
Use it to resume tasks, search prior context, maintain goals and checkpoints, and record handoff or recovery information.
Why use it?
It helps continue work after a session ends without treating saved memories as more reliable than the current files, tests, and instructions.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions subagents; mentions Codex.

Good fit Use it to resume tasks, search prior context, maintain goals and checkpoints, and record handoff or recovery information.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/novasplace/csm/csm-continuity
Install

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.

Any agent
npx skills add NovasPlace/CSM --skill csm-continuity
Clone the repo
git clone --depth 1 https://github.com/NovasPlace/CSM

Made for: Codex.

Wrote 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.

agentmods badge for csm-continuity

README.md
[![agentmods](https://agentmods.dev/badge/skills/novasplace/csm/csm-continuity.svg)](https://agentmods.dev/skills/novasplace/csm/csm-continuity)
Your own site
<a href="https://agentmods.dev/skills/novasplace/csm/csm-continuity"><img src="https://agentmods.dev/badge/skills/novasplace/csm/csm-continuity.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 681 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Privilege Escalation · line 22
    Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
    Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.00681
Opus 5 $0.00030 $0.00341
Sonnet 5 $0.00012 $0.00136
Haiku 4.5 $0.00006 $0.00068

Measured 8d ago against content hash a3ed8622fbfa, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

csm-continuity 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 8d 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.

plugins/cross-session-memory-bridge/skills/csm-continuity/SKILL.md · 44 lines

How it starts

The opening of the file, as written. The whole thing — 44 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CSM Continuity

Use the plugin's full CSM runtime without treating memory as more authoritative than the current workspace. Native hooks automatically capture session, prompt, tool, compaction, subagent, and stop events; do not duplicate routine hook capture manually.

Start or resume work

  1. Resolve projectRoot to the current workspace root. Keep every read and write scoped to it.
  2. Call csm_runtime_status before the first memory operation. If the runtime is unavailable or points at the wrong provider, stop and report the configuration problem.
  3. If the injected onboarding and <agent_reentry_context> are insufficient, call csm_onboard_agent, csm_reentry_preview, or bridge_resume_context with projectRoot and the user's current task.
  4. Use csm_memory_search, csm_memory_context, recall_lessons, or get_context_brief only when the resumed context needs focused evidence.
  5. Verify recalled claims against current files, tests, and user instructions before acting on them.

Preserve useful state

  • Native tool hooks already record tool evidence, work-journal entries, experience packets, AgentBook events, and living-state triggers. Use bridge_sync_turn only for an additional durable milestone that automatic capture cannot infer.
  • Use memory_lesson for a reusable lesson and save_memory for an explicitly useful durable record.
  • Never persist credentials, secrets, access tokens, private keys, or unnecessary sensitive content. Redact before saving.
  • Prefer evidence and provenance over broad claims. Current repository state remains the source of truth.

Checkpoint and hand off

  1. Before compaction, interruption, or a risky transition, inspect csm_context_pressure when an explicit message snapshot is available.
  2. Use create_checkpoint when the current state would be expensive to reconstruct.
  3. Before stopping or transferring work, sync the final durable milestone and call bridge_handoff_summary.
  4. Make the handoff concrete: outcome, files changed, verification, open risks, and next action.

Read the full file on GitHub · 44 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 8d ago First seen · 44 lines · 60 tokens per session scan A a3ed8622fbfa

Subscribe to this mod's changes

csm-continuity is a skill published in the GitHub repository NovasPlace/CSM (42 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 681 once invoked, about $0.0003 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.

Related

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…

Opita-Code/dark-memory-mcp · 353 tokens

mem9

Persistent cloud memory plugin for OpenClaw. This document routes setup, troubleshooting, and uninstall flows and defines config boundaries.

mem9-ai/mem9 · 27 tokens

usage

Wren Engine CLI workflow guide for AI agents. Answer data questions end-to-end using the wren CLI: gather schema context, recall past queries, write SQL through the MDL semantic layer, execute, and learn from confirmed results. Use when: user asks a data question, requests a report or analysis, asks about metrics…

Canner/WrenAI · 156 tokens

kip-cognitive-nexus

Persistent graph-based memory for AI agents via KIP (Knowledge Interaction Protocol). Provides retrieval-first memory operations (KQL), durable writes (KML), schema discovery (META), and memory hygiene patterns. Use whenever the agent needs to consult or update persistent memory, especially for: remembering user…

ldclabs/KIP · 90 tokens

mstar-compound-refresh

A knowledge-maintenance workflow for reviewing project knowledge documents, removing outdated material, merging overlaps, or creating a starter knowledge set from a codebase.

btspoony/mstar-harness · 174 tokens

add-editor

Wire Deus's memory + evolution layers into an external code editor (Zed and other ACP/MCP clients) so the editor's own agent gains Deus's vault recall and self-improving reflexion loop. Configuration only — no new code. Triggers on "add editor", "use Deus in my editor", "zed integration", "editor integration", "wire…

sliamh11/Deus · 89 tokens