update

update is a skill for Claude Code from eigenlegal/counsel-os. It costs 25 tokens per session (3,913 once invoked), scanned A, original, MIT.

A guided update process for Counsel OS, a legal-work knowledge system, that refreshes its plugin and legal content safely.

In plain words
What is it for?
Use it to find the legal root, migrate older configuration, and review changes to legal notes and practices.
Why use it?
It helps avoid using outdated guidance or changing the wrong legal files. It also handles upgrades from older configuration formats and asks before changing user-owned knowledge.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions Claude Code.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the counsel-os plugin — 9 skills shipped together

Good fit Use it to find the legal root, migrate older configuration, and review changes to legal notes and practices.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add eigenlegal/counsel-os
Claude Code
/plugin install counsel-os

Made for: Claude Code.

Or install counsel-os, the plugin that ships this one along with the rest of its 9 skills.

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 update

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/eigenlegal/counsel-os/update"><img src="https://agentmods.dev/badge/skills/eigenlegal/counsel-os/update.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,913 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.
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 $0.00025 $0.03913
Opus 5 $0.00013 $0.01956
Sonnet 5 $0.00005 $0.00783
Haiku 4.5 $0.00003 $0.00391

Measured 8d ago against content hash 78ec52b0c015, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

update 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.

skills/update/SKILL.md · 313 lines

How it starts

The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update — Skill-First Sync

Counsel OS updates are LLM-orchestrated. The skill decides what is safe to do in the current runtime, explains each step, and asks before changing user-owned knowledge.

Step 0: Resolve Plugin Root

Resolve the plugin root first: the directory containing this skill. You need this to distinguish plugin documentation from the user's legal root and to find shipped content.

Step 1: Migrate Config If Needed

This is a one-time migration path for users upgrading from earlier Counsel OS versions. It is intentionally limited to /counsel-os:update; normal counsel/setup path discovery remains strict and does not silently accept legacy config.

Current config format

A valid legal-root config is marked:

counsel-os-config: true
legal_root: /absolute/path/to/legal/root

Migration trigger

First try the Finding the Legal Root procedure in skills/counsel/SKILL.md.

  • If it finds a marked config, skip this migration.
  • If it finds no marked config, attempt the migration below.
  • If it finds multiple marked configs, ask the user which one to use and skip migration.

Migration sources

Check these sources in order. A source may be read only for this migration, not as a recurring fallback.

  1. Pointer file at ~/.counsel-os/legal-root if home-directory access is available. If it points to a directory that exists, treat that directory as the candidate legal root.
  2. Legacy plugin config at {plugin_root}/config.local.md, if present. Read only legal_root:, entities_path:, matters_path:, and entity_properties: fields.
  3. User-provided path. If no source is found, ask: "Where is your existing Counsel OS legal root?"

Do not scan arbitrary unmarked config.md files. That was the old failure mode: plugin documentation or unrelated project files could be mistaken for user config.

Candidate validation

Before writing anything, validate the candidate legal root:

  • The path is outside the plugin root.
  • The directory exists, or the user approved creating it.
  • Prefer candidates containing at least one Counsel OS directory: law/, practice/, matters/, memory/, or entities/.
  • If the candidate has an existing config.md, preserve optional overrides from it only if it appears to be user config. Do not preserve unrelated prose or plugin docs.

Read the full file on GitHub · 313 lines

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 Changed · +2 lines 78ec52b0c015
  2. 12d ago First seen · 311 lines · 25 tokens per session scan A 7c7259d99ccf

Subscribe to this mod's changes

update is a skill published in the GitHub repository eigenlegal/counsel-os (24 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 3,913 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.

Related

Other skills, from other repositories

specification-writing

A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.

wanshuiyin/Auto-claude-code-research-in-sleep · 49 tokens

regulatory-research-fallback

Fallback workflow for regulatory research when web extraction tools fail on government PDFs.

HKUDS/OpenSpace · 20 tokens

x-scorecard

OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.

x-cmd/x-cmd · 57 tokens

gesellschaftsrechtliche-satzungen-agb

Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.

Klotzkette/claude-fuer-deutsches-recht · 69 tokens

memstack-business-gdpr

Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…

cwinvestments/memstack · 121 tokens

nda-review

Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…

LegalQuants/lq-ai · 79 tokens