New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Official agent skill

Escalation Flagger

by anthropics in anthropics/claude-for-legal

Route a contract issue to the right approver per the escalation matrix in ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md, and draft the ask.

OfficialApache-2.0Auto-check passedAgent Workflows

Install Escalation Flagger

skills CLI
$ npx skills add anthropics/claude-for-legal --skill escalation-flagger -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install anthropics/claude-for-legal escalation-flagger --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/anthropics/claude-for-legal.git skills-src && mkdir -p .claude/skills && cp -r skills-src/commercial-legal/skills/escalation-flagger .claude/skills/escalation-flagger && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
escalation-flagger
GitHub stars
9.6k
Used in
1 other repo
Token cost
~2.2k tokens
SKILL.md length
897 words
Files
1
Skills in repo
147
Repo updated
First seen
Licence
Apache-2.0

At a glance

Route a contract issue to the right approver per the escalation matrix in ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md, and draft the ask.

  • Works in 5 steps: Characterize the issue → Match to the matrix → Name the approver → …
  • The user says who needs to approve this
  • SKILL.md covers Instructions, Examples, Matter context and Purpose, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Escalation Flagger is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization. Route a contract issue to the right approver per the escalation matrix in ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md, and draft the ask. Use when the user says "who needs to approve this", "escalate this", "does this need GC sign-off", "route this for approval", or when another skill finds an issue that exceeds the reviewer's authority.

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows, covering Agent instruction files. The repository describes itself as: A suite of plugins for legal workflows. The licence is Apache-2.0.

When your agent uses it

  • The user says who needs to approve this
  • Does this need GC sign-off
  • Route this for approval
  • Another skill finds an issue that exceeds the reviewers authority

Example prompts

  • “who needs to approve this”
  • “escalate this”
  • “does this need GC sign-off”
  • “/escalation-flagger”

Workflow steps

5 steps, taken from the step headings in SKILL.md.

  1. Characterize the issue
  2. Match to the matrix
  3. Name the approver
  4. Draft the ask
  5. Record the escalation

What it can do on your machine

Read from SKILL.md and the folder at commit 4a6c651. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Escalation Flagger loads about 2.2k tokens when it runs. Until then it costs about 96 tokens; SKILL.md has 897 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~96
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from anthropics/claude-for-legal at commit 4a6c651, republished under its Apache-2.0 licence (© anthropics). 897 words, ~2,165 tokens.

Download SKILL.mdSave it as .claude/skills/escalation-flagger/SKILL.md (or your agent's skills folder).
name
escalation-flagger
description
Route a contract issue to the right approver per the escalation matrix in `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`, and draft the ask. Use when the user says "who needs to approve this", "escalate this", "does this need GC sign-off", "route this for approval", or when another skill finds an issue that exceeds the reviewer's authority.
argument-hint
[describe the issue, or reference a review memo]

/escalation-flagger

Names the approver for a contract issue per the ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md escalation matrix and drafts the message so you're not writing "hey got a sec" at 5pm.

Instructions

  1. Load ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md → Escalation section. If missing, say so — the practice profile needs editing.

  2. Characterize the issue: dollar threshold / term deviation / automatic trigger / business decision.

  3. Match to matrix, name the approver. Be specific — a person or role, not "legal leadership."

  4. Draft the ask per the template below: what the contract says, what playbook says, options with recommendation, decision-by date.

  5. Do not send. Draft it, show it, let the lawyer send.

Examples

/commercial-legal:escalation-flagger
The Acme MSA has uncapped liability — who approves and what do I say?
/commercial-legal:escalation-flagger
Reference: acme-review-memo.md
Issue: §8.2 indemnity carveouts

Matter context

Matter context. Check ## Matter workspaces in the practice-level CLAUDE.md. If Enabled is ✗ (the default for in-house users), skip the rest of this paragraph — skills use practice-level context and the matter machinery is invisible. If enabled and there is no active matter, ask: "Which matter is this for? Run /commercial-legal:matter-workspace switch <slug> or say practice-level." Load the active matter's matter.md for matter-specific context and overrides. Write outputs to the matter folder at ~/.claude/plugins/config/claude-for-legal/commercial-legal/matters/<matter-slug>/. Never read another matter's files unless Cross-matter context is on.

Purpose

Every contracts team has an escalation matrix, written or not. This skill reads the written one (in ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md), matches a contract issue against it, names the approver, and drafts the ask so the lawyer isn't writing "hey do you have a sec" messages at 5pm.

Load the matrix

Which side? Before matching to the matrix, determine which side the company is on for the contract whose issue is being escalated. Usually obvious: if the counterparty is a vendor/supplier providing goods or services, you're purchasing-side. If the counterparty is a customer buying your product/service, you're sales-side. If it's not obvious, ask. Read the matching playbook section (### Sales-side playbook or ### Purchasing-side playbook) to evaluate whether the term is inside fallbacks or triggers an automatic escalation — a term that's fine on one side can be a hard-no on the other. Note which side in the drafted ask so the approver knows which playbook was applied.

Read ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md → ## Escalation. If it's missing or vague, say so — the cold-start interview should have captured this, and if it didn't, the practice profile needs editing.

Expected structure:

Can approveThresholdEscalates toVia
ParalegalStandard terms, <$50KCounselSlack
CounselNon-standard but within fallbacks, <$500KGCSlack or email
GCEverything elseCFO/BoardMeeting

Plus automatic escalation triggers — things that escalate regardless of dollar value. Typically: unlimited liability, IP assignment, anything on the "never accept" lists.

Workflow

Step 1: Characterize the issue

What's being escalated?

  • Dollar threshold: Contract value exceeds someone's approval authority
  • Term deviation: A term is outside the playbook fallbacks — someone more senior needs to decide whether to accept
  • Automatic trigger: One of the always-escalate items is present
  • Business decision: Not a legal call — needs the business owner, not legal leadership

Don't escalate things that are actually fine. If the term is within the fallbacks in ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md, it doesn't need to go up.

Step 2: Match to the matrix
Is the issue an automatic trigger?
  → YES: escalate to [person named for that trigger]
  → NO: continue

Is the contract value above the reviewer's threshold?
  → YES: escalate to whoever has authority at that dollar level
  → NO: continue

Is the term deviation outside all documented fallbacks?
  → YES: escalate to whoever can approve non-standard terms
  → NO: reviewer can approve — no escalation needed
Step 3: Name the approver

Be specific. Not "escalate to legal leadership" — name the person or role from ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md. If the matrix doesn't name anyone for this situation, say so: "The escalation matrix doesn't cover [situation]. Suggest asking [GC name] who owns this."

Show full SKILL.md (352 more words)Show less
Step 4: Draft the ask

The approver should be able to decide from the message alone — no "let me pull up the contract."

markdown
**Escalating to:** [name]
**Via:** [Slack #channel / email / meeting — per `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`]
**Urgency:** [deadline if there is one]

---

Hey [name] —

Need your call on the [Counterparty] [agreement type]. [One sentence on deal context.]

**The issue:** [Plain English, one paragraph. What they want, why it's outside
our standard, what the risk actually is.]

**What the contract says:**
> "[exact quote]"

**What our playbook says:** [quote from `~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md`]

**Options:**
1. **Accept** — [one line on why this might be okay]
2. **Push back with:** "[proposed counter-language]" — [one line on likely counterparty reaction]
3. **Walk** — [one line on whether that's realistic given the business context]

**My recommendation:** [which option and why, briefly]

**Need a decision by:** [date, if there is a deadline]

[Link to full review memo]
Step 5: Record the escalation

If this team uses a ticket system or [CLM] approval workflows, log it. If not, note in the review memo that the escalation was sent, to whom, and when. The next person who reads the memo should see the status.

Calibration: when in doubt, escalate with a note

The cost of an unnecessary escalation is ~30 seconds of the approver's time — they read, say "fine, proceed," and the record shows they saw it. The cost of a missed escalation is signing an unapproved term, which is a one-way door. The costs are not symmetric. When in doubt, escalate.

The calibration for what warrants escalation lives in ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md, not in this skill. Check the playbook's stated position, its fallbacks, and its "automatic escalation regardless of dollar value" list:

  • Clearly inside the fallback range: no escalation needed.
  • Clearly outside the range, or on the automatic-escalation list: escalate.
  • Uncertain — the term is ambiguous, novel, or arguably inside the range but the argument is a stretch: escalate anyway, and note the uncertainty explicitly. The draft flags the specific question the approver needs to decide and why the skill couldn't confidently place it inside the fallback. The approver narrows; the skill does not.

Do not suppress an escalation because over-escalation might train approvers to skim. That's an approver-experience problem the attorney solves by adjusting thresholds in the playbook, not a problem the skill solves by making its own subjective call on a term it's uncertain about.

If a term comes up that the playbook doesn't address, don't guess the threshold — ask the reviewing attorney whether this class of issue should escalate, and offer to record the answer in ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md so future reviews are consistent.

What this skill does not do

  • It does not approve anything. It routes.
  • It does not decide between the options. The draft includes a recommendation but the approver decides.
  • It does not send the escalation message — it drafts it. The lawyer sends it after reading.

© anthropics, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in commercial-legal/skills/escalation-flagger of anthropics/claude-for-legal.

Open the folder on GitHubat commit 4a6c651

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in anthropics/claude-for-legal, which our catalogue first saw on October 7, 2026.

Compare with similar skills

Escalation Flagger next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Escalation Flagger compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Escalation Flagger this skillanthropics/claude-for-legal9.6k1 repos~2.2kAutomated safety check: PassApache-2.0
Using Agent Skillsaddyosmani/agent-skills103k4 repos~2.4kAutomated safety check: PassMIT
Claude ReflectBayramAnnakov/claude-reflect1.7k2 repos~627Automated safety check: PassMIT
Writing For Agentsbestofjs/bestofjs3.1k19 repos~2.7kAutomated safety check: PassMIT
Neat-Freak Knowledge CloseoutKKKKhazix/khazix-skills21k—~1.9kAutomated safety check: PassMIT
Task Observerrebelytics/one-skill-to-rule-them-all3.2k1 repos~12kAutomated safety check: PassCC-BY-4.0

Similar skills

  • Using Agent Skills

    addyosmani/agent-skills

    Meta-skill for choosing which workflow skill fits the task at hand, plus always-on habits: surface assumptions, stop on confusion, push back, keep it simple and stay in scope.

    103k GitHub starsUsed in 4 repos~2.4k tokens
    Agent WorkflowsAuto-check passed

  • Claude Reflect

    BayramAnnakov/claude-reflect

    Self-learning system that captures corrections during sessions and reminds users to run /reflect to update CLAUDE.md.

    1.7k GitHub starsUsed in 2 repos~627 tokens
    Agent WorkflowsAuto-check passed

  • Writing For Agents

    bestofjs/bestofjs

    Writing documents for agents. An agent skill from bestofjs/bestofjs.

    3.1k GitHub starsUsed in 19 repos~2.7k tokens
    Agent WorkflowsAuto-check passed

  • Neat-Freak Knowledge Closeout

    KKKKhazix/khazix-skills

    Brings project docs, agent rule files, authorized memory and leftover workspace files back in line with what the code and runtime actually do at the end of a work session.

    21k GitHub stars~1.9k tokensUpdated 7 days ago
    Agent WorkflowsAuto-check passed

  • Task Observer

    rebelytics/one-skill-to-rule-them-all

    Monitors task execution for skill improvement opportunities.

    3.2k GitHub starsUsed in 1 repo~12k tokens
    Agent WorkflowsAuto-check passed

  • SkillOpt Sleep Cycle

    microsoft/SkillOpt

    Official

    Runs an on-demand or nightly sleep cycle that reviews past Claude Code sessions and proposes validated updates to CLAUDE.md and skills.

    18k GitHub stars~2.3k tokensUpdated 2 days ago
    Agent WorkflowsAuto-check passed

More from anthropics/claude-for-legal

All 147 skills in this repo

  • Legal Clinic Client Intake

    anthropics/claude-for-legal

    Official

    Structures a legal clinic client intake interview and produces a case summary with cross-area issue spotting, conflict flags and triage classification.

    9.6k GitHub starsUsed in 3 repos~3.2k tokens
    Auto-check passed

  • Supervisor Review Queue

    anthropics/claude-for-legal

    Official

    Holds student work in a queue for a legal clinic professor to approve, edit-then-approve or return before anything reaches clients or courts.

    9.6k GitHub starsUsed in 3 repos~1.1k tokens
    Auto-check passed

  • Tabular Document Review

    anthropics/claude-for-legal

    Official

    Builds a review grid with one row per document and one column per data point, each cell cited to a verbatim quote, built for M&A diligence and other batch reviews.

    9.6k GitHub starsUsed in 3 repos~4.3k tokens
    Auto-check passed

  • Product Launch Legal Review

    anthropics/claude-for-legal

    Official

    Runs a category-by-category legal review of a product launch from a PRD or tracker ticket, calibrated to your team's framework, and writes a review memo in house format.

    9.6k GitHub starsUsed in 2 repos~5k tokens
    Auto-check passed

  • Legal Skills Registry Browser

    anthropics/claude-for-legal

    Official

    Searches watched registries for community legal skills, shows matches with descriptions and offers the full SKILL.md before anything is installed.

    9.6k GitHub starsUsed in 2 repos~620 tokens
    Auto-check passed

  • Contract Renewal Tracker

    anthropics/claude-for-legal

    Official

    Shows which contracts renew soon and when notice must be sent by, working from a maintained renewal register, and warns about missed cancellation windows.

    9.6k GitHub starsUsed in 2 repos~3.1k tokens
    Auto-check passed

Categories

Questions about Escalation Flagger

What does Escalation Flagger do?

Route a contract issue to the right approver per the escalation matrix in ~/.claude/plugins/config/claude-for-legal/commercial-legal/CLAUDE.md, and draft the ask. Escalation Flagger is an agent skill from anthropics/claude-for-legal, published by the product's own GitHub organization.md, and draft the ask.

When should I use Escalation Flagger?

Escalation Flagger fits situations like: the user says who needs to approve this; does this need GC sign-off; route this for approval; another skill finds an issue that exceeds the reviewers authority.

How do I install Escalation Flagger in Claude Code?

Run `npx skills add anthropics/claude-for-legal --skill escalation-flagger -a claude-code`. Or copy the skill folder (commercial-legal/skills/escalation-flagger in anthropics/claude-for-legal) into .claude/skills/escalation-flagger in your project. Claude Code loads it when a task matches its description.

How do I install Escalation Flagger in Codex?

Run `npx skills add anthropics/claude-for-legal --skill escalation-flagger -a codex`. Or copy the skill folder (commercial-legal/skills/escalation-flagger in anthropics/claude-for-legal) into .agents/skills/escalation-flagger in your project. Codex loads it when a task matches its description.

Can I use Escalation Flagger in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add anthropics/claude-for-legal --skill escalation-flagger -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/escalation-flagger, .gemini/skills/escalation-flagger, .github/skills/escalation-flagger and .opencode/skills/escalation-flagger in your project.

What does Escalation Flagger need to run?

SKILL.md names no scripts, command-line tools or credentials: Escalation Flagger is instructions for the agent only.

Does Escalation Flagger access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Escalation Flagger safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Escalation Flagger use?

Escalation Flagger is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Escalation Flagger use?

About 2.2k tokens (SKILL.md is roughly 8.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Escalation Flagger?

Skills that share tags, products or a category with Escalation Flagger: Using Agent Skills (addyosmani/agent-skills, 103k stars), Claude Reflect (BayramAnnakov/claude-reflect, 1.7k stars), Writing For Agents (bestofjs/bestofjs, 3.1k stars) and Neat-Freak Knowledge Closeout (KKKKhazix/khazix-skills, 21k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Escalation Flagger?

anthropics (a GitHub organization, an official publisher) maintains it in anthropics/claude-for-legal, which has 9,617 GitHub stars. The repository holds 147 skills in this directory. The repository was last updated on September 29, 2026.

Source: anthropics/claude-for-legal on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.