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/demo)<a href="https://agentmods.dev/skills/eigenlegal/counsel-os/demo"><img src="https://agentmods.dev/badge/skills/eigenlegal/counsel-os/demo/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/demo"><img src="https://agentmods.dev/badge/skills/eigenlegal/counsel-os/demo.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 | $0.00168 | $0.02258 |
| Opus 5 | $0.00084 | $0.01129 |
| Sonnet 5 | $0.00034 | $0.00452 |
| Haiku 4.5 | $0.00017 | $0.00226 |
Grade C, and why
demo scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$DEMO_DIR" && mkdir -p "$DEMO_DIR" How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Demo — See Counsel OS Work
You are giving the user a short, honest look at what Counsel OS can do. There are two parts: a capability guide (what it does, with the exact command for each), and one offered live showpiece (review a bundled synthetic NDA against the user's own seeded positions, then produce a redline). Keep it tight — this is a first impression, not a tutorial.
Hard rules (do not break these)
- Zero writes to the user's vault. The demo never creates a matter, never calls the
rememberprimitive, and never writes, edits, or deletes anything under{legal_root}. After the demo, the vault must be byte-for-byte what it was before. This is a founder-level rule. - The sample document is synthetic. Use only the bundled
assets/sample-mutual-nda.docx(and its markdown twin). Never substitute a real matter, a real counterparty, or anything from the user's vault. - All artifacts go to a disposable scratch folder outside the vault (see Step 2). Nothing the demo produces lands in the practice tree.
- Describe, don't fabricate. The capability guide explains real commands; it does not invent matters, history, or facts.
Step 0: Resolve capabilities and the legal root
First, find the user's legal root — the showpiece reviews the NDA against their positions, so a configured practice must exist.
bash "${CLAUDE_PLUGIN_ROOT}/scripts/resolve_legal_root.sh"
-
Exit
0→ stdout is{legal_root}. Continue. -
Non-zero → no practice is configured yet. Do not run the showpiece against nothing. Say:
Counsel OS reviews documents against your standards, so let's set those up first — it takes about three minutes. Run
/counsel-os:setup, then come back and run/counsel-os:demoagain.Then stop.
Also detect, quietly, what the redline showpiece will be able to produce (used in Step 3):
- python-docx:
python3 -c "import docx"exits 0 - Microsoft Word (macOS):
/Applications/Microsoft Word.appexists - User name:
{legal_root}/practice/profile.mdhas a real name (not a bracket placeholder)
What ships with it
2 files 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.
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.
- 8d ago Changed adcf1c896ecb
- 12d ago First seen · 113 lines · 168 tokens per session scan C d93310be4088
demo is a skill published in the GitHub repository eigenlegal/counsel-os (24 stars, last pushed yesterday), licensed MIT. It adds 168 tokens to every session and 2,258 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). 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.
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.
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…
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…