csm-governance

csm-governance is a skill for Claude Code from NovasPlace/CSM. It costs 43 tokens per session (320 once invoked), scanned A, original, MIT.

A set of procedures for reviewing and cleaning up Cross-Session Memory, which stores project information across separate coding sessions. It detects duplicates, suggests archive candidates, and checks recall quality before any changes.

In plain words
What is it for?
Use it to preview memory reports, review duplicate or outdated entries, and—after approval—merge exact duplicates or archive selected candidates.
Why use it?
It helps keep saved project context useful without silently deleting information or mixing memories from different projects.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the cross-session-memory plugin — 2 skills, 12 commands, 3 agents shipped together

Good fit Use it to preview memory reports, review duplicate or outdated entries, and—after approval—merge exact duplicates or archive selected candidates.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/novasplace/csm/csm-governance
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-governance
Clone the repo
git clone --depth 1 https://github.com/NovasPlace/CSM

Made for: Claude Code.

Or install cross-session-memory, the plugin that ships this one along with the rest of its 2 skills, 12 commands, 3 agents.

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-governance

README.md
[![agentmods](https://agentmods.dev/badge/skills/novasplace/csm/csm-governance/github.svg)](https://agentmods.dev/skills/novasplace/csm/csm-governance)
Your own site
<a href="https://agentmods.dev/skills/novasplace/csm/csm-governance"><img src="https://agentmods.dev/badge/skills/novasplace/csm/csm-governance/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.

agentmods 80×15 button for csm-governance

Your own site · 80×15
<a href="https://agentmods.dev/skills/novasplace/csm/csm-governance"><img src="https://agentmods.dev/badge/skills/novasplace/csm/csm-governance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 320 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 pass 7 Sept 2026
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 $0.00043 $0.00320
Opus 5 $0.00022 $0.00160
Sonnet 5 $0.00009 $0.00064
Haiku 4.5 $0.00004 $0.00032

Measured 11d ago against content hash 60cb134cb546, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

csm-governance 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.

plugins/cross-session-memory/skills/csm-governance/SKILL.md · 29 lines

What it actually says

CSM Memory Governance

Keep project memory clean without losing provenance. Every governance action is scoped to the current projectRoot.

Always preview first

  1. Resolve projectRoot to the current workspace root.
  2. Run the read-only reports before any change: csm_memory_governance_report, csm_memory_dedup_detect, csm_memory_candidate_report, csm_memory_archive_candidate_report, and csm_recall_quality_report.
  3. Present findings and a concrete plan. Ask for approval on the specific candidates before mutating.

Mutation rules

  • csm_memory_merge is exact-match only. It supersedes duplicates and preserves originals; it never deletes. Merge only user-approved candidates.
  • csm_memory_delete, memory_cleanup, candidate approval/rejection, and embedding backfill are mutations. Perform them only on an explicit, specific request — never in bulk from a heuristic.
  • Never merge on embedding similarity alone; exact content detection catches the real duplication at current scale.

Boundaries

  • Do not cross project boundaries.
  • Never surface or persist secrets, credentials, or sensitive content.
  • Memory is evidence and provenance; the current repository state is the source of truth.

For a focused, autonomous pass, delegate to the csm-archivist agent.

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. 11d ago First seen · 29 lines · 43 tokens per session scan A 60cb134cb546

Subscribe to this mod's changes

csm-governance is a skill published in the GitHub repository NovasPlace/CSM (42 stars, last pushed 3d ago), licensed MIT. It adds 43 tokens to every session and 320 once invoked, about $0.0002 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

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

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

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