Developer Tools

Is Agentic

is-agentic-pp-cli

Turn Is Agentic reports into durable, scriptable readiness evidence.

Printed by @SomSamantray (Som Samantray)

Install

npx — recommended

npx -y @mvanhorn/printing-press-library install is-agentic

Installs the CLI binary and the agent skill (Claude Code, Codex, Cursor, Gemini CLI, Copilot, and more). Add --cli-only or --skill-only for one half. Requires Node.

Hermes

hermes skills install mvanhorn/printing-press-library/cli-skills/pp-is-agentic --force

From the Hermes CLI. Inside a chat session use /skills install with the same path.

OpenClaw

Install the pp-is-agentic skill from https://github.com/mvanhorn/printing-press-library/tree/main/cli-skills/pp-is-agentic. The skill defines how its required CLI can be installed.

Paste this to your OpenClaw agent — the skill describes how to install its CLI.

Claude Desktop

This CLI ships an MCPB bundle. Download the latest release .mcpb and double-click it — Claude Desktop walks you through the install.

View source on GitHub →

Turn Is Agentic reports into durable, scriptable readiness evidence.

Retrieve the official report with the same read-only contract as the upstream CLI, then keep local history, diffs, fleet comparisons, policy gates, issue lifecycles, and exportable evidence beside it. The API remains the source of truth; the local layer makes repeated engineering work compound.

Learn more at Is Agentic.

Created by @SomSamantray (Som Samantray).

Quick Start

# Verify the generated CLI and public-service configuration without network access.
is-agentic-pp-cli doctor --dry-run

# Preview the canonical report request safely.
is-agentic-pp-cli report get-is-agentic-v1 --url https://is-agentic.com --dry-run

# Fetch the latest completed report as structured JSON.
is-agentic-pp-cli report get-is-agentic-v1 --url https://is-agentic.com --json

Unique Features

These capabilities aren't available in any other tool for this API.

Local evidence that compounds

history — Keep a local, timestamped ledger of readiness reports and their provenance.

Choose this when you need an auditable local timeline instead of one ephemeral API response.
```
is-agentic-pp-cli history --json --agent
```
diff — See which readiness scores and findings changed between two retained audits.

Choose this after a deployment to verify whether agent-readiness regressions were introduced or fixed.
```
is-agentic-pp-cli diff --target https://is-agentic.com --json --agent
```
issues — Track when readiness findings first appeared, last appeared, were fixed, or regressed.

Choose this to turn recurring findings into a remediation queue with honest history.
```
is-agentic-pp-cli issues --target https://is-agentic.com --json --agent
```

Release and fleet controls

check — Fail CI with an explicit, machine-readable readiness policy decision.

Choose this when a release pipeline must enforce readiness instead of merely displaying it.
```
is-agentic-pp-cli check --target https://is-agentic.com --min-score 80 --json --agent
```
portfolio — Compare a fleet of public sites in one sortable score and issue matrix.

Choose this for platform or agency work spanning multiple public targets.
```
is-agentic-pp-cli portfolio --targets https://is-agentic.com,https://example.com --json --agent
```
portfolio — Refresh many targets with bounded concurrency, deduplication, and Retry-After-aware pacing.

Choose this for repeatable fleet refreshes that must respect the public 120-per-minute quota.
```
is-agentic-pp-cli portfolio --file sites.txt --max-requests 50 --json --agent
```

Portable audit artifacts

evidence — Package a report and its provenance into a portable evidence artifact.

Choose this when an audit must travel with a review, ticket, or release artifact.
```
is-agentic-pp-cli evidence --target https://is-agentic.com --json
```

Recipes

Fetch one report

is-agentic-pp-cli report get-is-agentic-v1 --url https://is-agentic.com --json --agent

Return the current report in a compact agent-friendly shape.

Compare a small fleet

is-agentic-pp-cli portfolio --targets https://is-agentic.com,https://example.com --json --agent --select target,score,score_label

Compare targets while selecting only the fields needed for a decision.

Gate a release

is-agentic-pp-cli check --target https://is-agentic.com --min-score 80 --json --agent

Enforce a local minimum score with a structured decision.

Usage

Run is-agentic-pp-cli --help for the full command reference and flag list.

Paths & environment variables

This CLI separates local files into four path kinds:

Kind	Contents
`config`	User-editable settings such as `config.toml` and saved profiles
`data`	Durable local data such as `data.db`
`state`	Runtime state such as persisted queries, jobs, and `teach.log`
`cache`	Regenerable HTTP/cache files

Each kind resolves independently. The ladder is:

Per-kind env var: IS_AGENTIC_CONFIG_DIR, IS_AGENTIC_DATA_DIR, IS_AGENTIC_STATE_DIR, or IS_AGENTIC_CACHE_DIR
--home <dir> for this invocation
IS_AGENTIC_HOME for a flat relocated root
XDG env vars: XDG_CONFIG_HOME, XDG_DATA_HOME, XDG_STATE_HOME, XDG_CACHE_HOME
Platform defaults matching existing installs

For containers and agent sandboxes, prefer a single relocated root:

export IS_AGENTIC_HOME=/srv/is-agentic
is-agentic-pp-cli doctor

Under IS_AGENTIC_HOME=/srv/is-agentic, the four dirs resolve to /srv/is-agentic/config, /srv/is-agentic/data, /srv/is-agentic/state, and /srv/is-agentic/cache.

MCP servers do not receive CLI flags from the host. Put relocation in the host env block:

{
  "mcpServers": {
    "is-agentic": {
      "command": "is-agentic-pp-mcp",
      "env": {
        "IS_AGENTIC_HOME": "/srv/is-agentic"
      }
    }
  }
}

Precedence matters in fleets: an ambient per-kind variable such as IS_AGENTIC_DATA_DIR overrides an explicit --home for that kind. Use IS_AGENTIC_HOME or the per-kind variables for durable fleet relocation; treat --home as the weaker per-invocation lever.

Relocation is one-way. Unsetting IS_AGENTIC_HOME does not move files back to platform defaults, and doctor cannot find files left under a former root. Move the files manually before unsetting relocation variables.

Existing installs keep working because the platform-default rung matches the legacy layout. Run is-agentic-pp-cli doctor --fail-on warn to check path warnings in automation.

Commands

report

Read completed public Is Agentic reports.

is-agentic-pp-cli report get-is-agentic-legacy - Deprecated compatibility alias for GET /api/v1/report. Responses include the RFC 9745 Deprecation header and a successor-version link.
is-agentic-pp-cli report get-is-agentic-v1 - Returns one latest completed stored report for a public HTTP or HTTPS URL without launching a scan. This is a single-resource read operation: it has no request body, pagination, idempotency key, or asynchronous job.

Self-learning loop

This CLI caches per-question discovery so repeat queries skip the walk and structurally similar queries get answered via entity substitution. The loop also self-captures: every invocation is journaled locally, and failed-flag corrections plus fresh teaches surface as candidates on the next recall for confirm/reject judgment. Agents call recall before discovery and fire teach & after answering. See the ## Automatic learning section in SKILL.md for the full protocol.

is-agentic-pp-cli recall <query> - Look up cached resources for a query before running discovery
is-agentic-pp-cli teach - Record a query -> resource mapping (silent on success, safe to background with &)
is-agentic-pp-cli learnings list - Inspect taught rows
is-agentic-pp-cli learnings forget <query> - Undo a teach
is-agentic-pp-cli learnings candidates - List auto-captured candidates awaiting confirm/reject
is-agentic-pp-cli learnings stats - Local loop metrics: recall hit rate, teach-to-reuse, playbook resolution, candidate counts
is-agentic-pp-cli teach-pattern - Install a query/resource template up front
is-agentic-pp-cli teach-lookup - Add an entity mapping (e.g. country code, team alias) for pattern substitution

Pass --no-learn or set IS_AGENTIC_NO_LEARN=true to disable the loop for deterministic flows.

The local store's schema version stamp is one-way: once this version of is-agentic-pp-cli opens the database, older binaries refuse it with a version error — upgrade the binary rather than downgrading.

Output Formats

# Human-readable table (default in terminal, JSON when piped)
is-agentic-pp-cli report get-is-agentic-legacy --url https://example.com

# JSON for scripting and agents
is-agentic-pp-cli report get-is-agentic-legacy --url https://example.com --json
# Filter to specific fields
is-agentic-pp-cli report get-is-agentic-legacy --url https://example.com --json --select details,id,name

# Dry run — show the request without sending
is-agentic-pp-cli report get-is-agentic-legacy --url https://example.com --dry-run

# Agent mode — JSON + compact + no prompts in one flag
is-agentic-pp-cli report get-is-agentic-legacy --url https://example.com --agent

Agent Usage

This CLI is designed for AI agent consumption:

Non-interactive - never prompts, every input is a flag
Pipeable - --json output to stdout, errors to stderr
Filterable - --select <field>[,<field>...] returns only fields you need
Previewable - --dry-run shows the request without sending
Read-only by default - this CLI does not create, update, delete, publish, send, or mutate remote resources
Local evidence - report and portfolio commands populate a local SQLite history for history/diff/issues; this API has no bulk sync endpoint
Agent-safe by default - no colors or formatting unless --human-friendly is set

Exit codes: 0 success, 2 usage error, 3 not found, 5 API error, 7 rate limited, 10 config error.

Health Check

is-agentic-pp-cli doctor

Verifies configuration and connectivity to the API.

Configuration

Run is-agentic-pp-cli doctor to see the resolved config, data, state, and cache directories. The platform-default config path is ~/.config/is-agentic-public-pp-cli/config.toml; --home, IS_AGENTIC_HOME, and per-kind env vars can relocate it.

Static request headers can be configured under headers; per-command header overrides take precedence.

Troubleshooting

Not found errors (exit code 3)

Check the resource ID is correct
Run the list command to see available items

API-specific

report_not_found — Open the canonical report URL printed in the error, start the scan there, then retry the CLI.
rate_limit_exceeded — Honor Retry-After and lower portfolio concurrency or max requests.
temporary unavailability — Retry without launching a new scan; the service may be refreshing stored evidence.