axonflow-recover-verify

axonflow-recover-verify is a command for Claude Code from getaxonflow/axonflow-claude-plugin. It costs 22 tokens per session (410 once invoked), scanned A, original, MIT.

A command that uses a recovery token from an AxonFlow email to create new tenant credentials. It then saves those credentials in the plugin's local configuration.

In plain words
What is it for?
Finishing AxonFlow tenant recovery, creating a fresh tenant ID and secret, and storing them for later governed tool calls.
Why use it?
It completes recovery after the user receives the email, so they do not have to manually configure the new credentials. The token must be copied from the link in the email.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

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 axonflow plugin — 7 skills, 10 commands, 2 hooks, 1 MCP server shipped together

Good fit Finishing AxonFlow tenant recovery, creating a fresh tenant ID and secret, and storing them for later governed tool calls.

Compare 6 commands 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 getaxonflow/axonflow-claude-plugin
Claude Code
/plugin install axonflow

Made for: Claude Code.

Or install axonflow, the plugin that ships this one along with the rest of its 7 skills, 10 commands, 2 hooks, 1 MCP server.

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 axonflow-recover-verify

README.md
[![agentmods](https://agentmods.dev/badge/commands/getaxonflow/axonflow-claude-plugin/axonflow-recover-verify/github.svg)](https://agentmods.dev/commands/getaxonflow/axonflow-claude-plugin/axonflow-recover-verify)
Your own site
<a href="https://agentmods.dev/commands/getaxonflow/axonflow-claude-plugin/axonflow-recover-verify"><img src="https://agentmods.dev/badge/commands/getaxonflow/axonflow-claude-plugin/axonflow-recover-verify/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 axonflow-recover-verify

Your own site · 80×15
<a href="https://agentmods.dev/commands/getaxonflow/axonflow-claude-plugin/axonflow-recover-verify"><img src="https://agentmods.dev/badge/commands/getaxonflow/axonflow-claude-plugin/axonflow-recover-verify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 410 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 $0.00022 $0.00410
Opus 5 $0.00011 $0.00205
Sonnet 5 $0.00004 $0.00082
Haiku 4.5 $0.00002 $0.00041

Measured 10d ago against content hash fb36b38d7466, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

axonflow-recover-verify 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 10d 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.

commands/axonflow-recover-verify.md · 21 lines

What it actually says

Consume a magic-link token issued by /axonflow-recover (or the auto-sent recovery email). On success the agent mints a fresh tenant_id + secret bound to the same email and the plugin persists them locally so subsequent governed calls authenticate as the recovered tenant.

Argument: $ARGUMENTS

Parse the argument as <token>. Tokens are 64-character hex strings. If missing or shorter than 32 characters, ask the user for the token they received in the magic-link email — they should copy the token=… value from the URL, not the URL itself.

Then run the plugin's recover-verify.sh helper using the Bash tool. The helper POSTs to /api/v1/recover/verify with Content-Type: application/json (programmatic flow — no HTML page in the loop), validates the response shape, and persists the new credentials atomically to ~/.config/axonflow/try-registration.json (mode 0600 inside a 0700 directory — same file the Community-SaaS bootstrap reads on every hook invocation).

$CLAUDE_PLUGIN_ROOT/scripts/recover-verify.sh '<token>'

On success the script writes a single OK tenant_id=… email=… endpoint=… expires_at=… line followed by the platform's note and a reminder about the previous tenant's audit history. Surface those lines verbatim.

On failure (HTTP 401 = token invalid/expired/already consumed; 403 = per-email cap reached; 5xx = server error) the script exits non-zero with ERR … lines that include the platform's error message. Surface them verbatim and tell the user to start over with /axonflow-recover <email> if they still need to recover.

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. 10d ago First seen · 21 lines · 22 tokens per session scan A fb36b38d7466

Subscribe to this mod's changes

axonflow-recover-verify is a command published in the GitHub repository getaxonflow/axonflow-claude-plugin (4 stars, last pushed 4d ago), licensed MIT. It adds 22 tokens to every session and 410 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 2026-08-31.

Related

Other commands, from other repositories