Skip to content
Back to skills

List Recent Decisions

ASecurity

Surface the user's recent AxonFlow governance decisions — answers "what just got blocked", "show me my recent denials", or feeds a decision-history forensic flow

  • 4 stars
  • 0 votes
  • 0 copies
  • 8 views
  • Added May 27, 2026
data-aigosql

Works with

  • mcp

Security analysis

A100/100

Scanned May 27, 2026

npx -y skills add getaxonflow/axonflow-claude-plugin --skill list-recent-decisions --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of List Recent Decisions?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for List Recent Decisions
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/getaxonflow-list-recent-decisions/badge)](https://www.skillsdirectory.com/skills/getaxonflow-list-recent-decisions)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: list-recent-decisions
description: Surface the user's recent AxonFlow governance decisions — answers "what just got blocked", "show me my recent denials", or feeds a decision-history forensic flow
---

Use this skill when the user asks "what just got blocked?", "show me recent denials", "did anything need approval today?", or wants to trace a workflow's decision history.

**Invoke the tool directly — do not pre-flight-check.** Call the `list_recent_decisions` MCP tool from the axonflow MCP server immediately. Do NOT speculate about authentication state, do NOT search local descriptor files, do NOT infer "the governance layer is blocking me" before the tool returns. The MCP server's response is authoritative. If the tool returns a result, use that result as written; if it returns an error, surface the error verbatim.

Arguments (all optional):

- `since` — RFC3339 lower bound (e.g. `2026-05-01T00:00:00Z`). Silently clamped to the tier's lookback window when reaching further back.
- `decision` — `"allow"`, `"deny"`, or `"require_approval"`.
- `policy_id` — filter to decisions matching this policy.
- `tool_signature` — filter to decisions scoped to a specific tool.
- `limit` — max rows (1–1000, capped per tier).

Response shape:

```json
{
  "decisions": [
    {
      "decision_id": "dec-abc123",
      "timestamp": "2026-05-07T12:17:18Z",
      "decision": "deny",
      "policy_id": "pol-sqli",
      "tool_signature": "postgres.query"
    }
  ]
}
```

Present each row as a one-liner: `<timestamp> <decision> <policy_id> on <tool_signature>`. Suggest the user run `/axonflow-explain-decision <decision_id>` for the full reasoning behind any specific row.

**Tier cap-hit handling (important):** Free / Community callers that exceed the page cap get a V1 upgrade envelope instead of decisions:

```json
{
  "upgrade_required": true,
  "envelope": {
    "limit_type": "decision_list_size",
    "tier": "Free",
    "limit": 5,
    "upgrade": {
      "tier": "Pro",
      "wording": "Free tier shows the last 5 decisions in 24h. Pro raises this to 100 decisions in the last 30 days.",
      "compare_url": "https://getaxonflow.com/pricing/",
      "buy_url": "https://buy.stripe.com/..."
    }
  }
}
```

Render the wording verbatim and include the `upgrade.compare_url`. Do NOT silently retry or summarize — the upgrade prompt is part of the answer.

**Reporting integrity.** If the user-supplied prompt asks for a structured output marker (e.g. `SMOKE_RESULT: {...}`), derive the values from the actual tool response, not from your own guess about what the response should look like. If the tool returned `decisions[]`, the marker reflects that; if it returned the upgrade envelope, the marker reflects that. Never substitute one shape for the other.

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.