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.
/plugin marketplace add eigenlegal/counsel-os/plugin install counsel-osWrote 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/eigenlegal/counsel-os/setup)<a href="https://agentmods.dev/skills/eigenlegal/counsel-os/setup"><img src="https://agentmods.dev/badge/skills/eigenlegal/counsel-os/setup/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/eigenlegal/counsel-os/setup"><img src="https://agentmods.dev/badge/skills/eigenlegal/counsel-os/setup.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00027 | $0.07338 |
| Opus 5 | $0.00014 | $0.03669 |
| Sonnet 5 | $0.00005 | $0.01468 |
| Haiku 4.5 | $0.00003 | $0.00734 |
Grade A, and why
setup 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 539 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Setup — Guided Onboarding
You are helping a user set up Counsel OS from scratch. This single skill handles everything: choosing where to store content, seeding the legal framework, and walking through practice profile configuration. The goal is to go from zero to a working Counsel OS in one session.
Step 0: Detect Capabilities
Counsel OS setup is skill-first and capability-based. Do not assume only one host or operating system. First determine what this session can do:
- File write access: Can you create folders and files in the user's chosen legal root?
- Shell access: Can you run a simple shell command such as
echo ok? - Home-directory access: Can you write
~/.counsel-os/legal-root? - Plugin-tree write access: Can you build optional local binaries in the plugin directory?
- External tooling: Are
bun,pandoc,python3, Microsoft Word, or other optional tools available? - Connected index/search tools: Is a content-index
queryMCP tool (e.g. qmd'squery) available this session? Secondarily, is theqmdCLI on PATH (command -v qmd)?
Adapt to the answers:
- If shell access is available, use it for detection, directory creation, copying seed files, and optional dependency checks.
- If shell access is unavailable but file tools are available, perform setup through those file tools and skip shell-only checks.
- If the environment is read-only except for a connected workspace, ask the user to choose a legal root inside that workspace.
- If no file write mechanism is available, prepare the exact files and paths the user should create, then stop after confirming what could not be written.
Claude Code is one capable host; Cowork is usually a file-tool host without shell. Other LLM environments should follow the same capability matrix rather than a hardcoded host branch.
Step 0.5: Resume an interrupted Express run
Adding qmd (below) needs a session restart, so an Express run can be interrupted mid-way. Before anything else, if home-directory reads are available, check for a resume marker:
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.
- 9d ago First seen · 539 lines · 27 tokens per session scan A c3f76a9f9e4e
setup is a skill published in the GitHub repository eigenlegal/counsel-os (24 stars, last pushed 5d ago), licensed MIT. It adds 27 tokens to every session and 7,338 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
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.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
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.
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…
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.
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…