Lindy Observability

What it does

When your agent uses it

• Setting up monitoring
• Building dashboards
• Configuring alerts
• Tracking agent performance over time

Example prompts

• “lindy monitoring”
• “lindy observability”
• “lindy metrics”
• “/lindy-observability”

Requirements

• A credential in LINDY_CALLBACK_SECRET
• Compatibility (from SKILL.md): Compatible with AI coding agents that can read Markdown and review monitoring configurations
• Pre-approved tools (allowed-tools): Read, Write, Edit

Workflow steps

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

1. 1Establish the Built-In View
2. 2Build the Monitoring Workflow
3. 3Collect Bounded Metrics
4. 4Query and Alert
5. 5Add Quality Regression Checks

What it can do on your machine

Read from SKILL.md and the folder at commit cfae287. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • Read
  • Write
  • Edit

  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 typescript and json).

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

• Network

  Links to these hosts (documentation or services it may open):

  • docs.lindy.ai

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

• Credentials

  Names these keys or tokens, usually read from environment variables:

  • LINDY_CALLBACK_SECRET

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

• Compatibility

  Compatible with AI coding agents that can read Markdown and review monitoring configurations

  From compatibility in the SKILL.md frontmatter.

Context cost

Lindy Observability loads about 2.5k tokens when it runs, and up to ~3.9k if it reads all its reference files. Until then it costs about 83 tokens; SKILL.md has 803 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~83

When it runs · the whole SKILL.md, loaded when a task matches

~2.5k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~3.9k

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

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 jeremylongshore/tons-of-skills-marketplace at commit cfae287, republished under its MIT licence (© jeremylongshore). 803 words, ~2,493 tokens.

name

lindy-observability

description

Monitor Lindy AI agent health, task success rates, and credit consumption. Use when setting up monitoring, building dashboards, configuring alerts, or tracking agent performance over time. Trigger with phrases like "lindy monitoring", "lindy observability", "lindy metrics", "lindy logging", "lindy dashboard".

allowed-tools

Read, Write, Edit

compatibility

Compatible with AI coding agents that can read Markdown and review monitoring configurations

version

1.20.0

license

MIT

author

Jeremy Longshore <jeremy@intentsolutions.io>

tags

saas, lindy, monitoring, observability, dashboard

import { timingSafeEqual } from 'node:crypto';
import express from 'express';
import { Counter, Histogram, Registry } from 'prom-client';

const app = express();
app.use(express.json({ limit: '4kb', strict: true }));

const callbackSecret = process.env.LINDY_CALLBACK_SECRET;
if (!callbackSecret || callbackSecret.trim().length < 32) {
  throw new Error('LINDY_CALLBACK_SECRET must contain at least 32 characters');
}

const agentKeys = new Set(
  (process.env.LINDY_MONITORED_AGENTS ?? '')
    .split(',')
    .map((value) => value.trim())
    .filter(Boolean),
);
if (agentKeys.size === 0) throw new Error('LINDY_MONITORED_AGENTS is empty');

type TaskStatus = 'succeeded' | 'failed' | 'canceled';
type MetricInput = { agent: string; status: TaskStatus; durationSeconds: number };
const statuses = new Set<TaskStatus>(['succeeded', 'failed', 'canceled']);

function authorized(header: string | undefined): boolean {
  if (!header?.startsWith('Bearer ')) return false;
  const actual = Buffer.from(header.slice('Bearer '.length));
  const expected = Buffer.from(callbackSecret);
  return actual.length === expected.length && timingSafeEqual(actual, expected);
}

function parseMetricInput(value: unknown): MetricInput | null {
  if (!value || typeof value !== 'object' || Array.isArray(value)) return null;
  const input = value as Record<string, unknown>;
  const allowed = new Set(['agent', 'status', 'durationSeconds']);
  if (Object.keys(input).some((key) => !allowed.has(key))) return null;
  if (typeof input.agent !== 'string' || !agentKeys.has(input.agent)) return null;
  if (typeof input.status !== 'string' || !statuses.has(input.status as TaskStatus)) return null;
  if (
    typeof input.durationSeconds !== 'number' ||
    !Number.isFinite(input.durationSeconds) ||
    input.durationSeconds < 0 ||
    input.durationSeconds > 86_400
  ) return null;
  return input as MetricInput;
}

const registry = new Registry();
const taskCounter = new Counter<'agent' | 'status'>({
  name: 'lindy_tasks_total',
  help: 'Total Lindy agent tasks',
  labelNames: ['agent', 'status'],
  registers: [registry],
});
const taskDuration = new Histogram<'agent'>({
  name: 'lindy_task_duration_seconds',
  help: 'Lindy task execution duration',
  labelNames: ['agent'],
  buckets: [1, 2, 5, 10, 30, 60, 120],
  registers: [registry],
});

app.post('/lindy/metrics', (req, res) => {
  if (!authorized(req.headers.authorization)) return res.sendStatus(401);
  const input = parseMetricInput(req.body);
  if (!input) return res.status(400).json({ error: 'invalid_metrics_schema' });

  taskCounter.inc({ agent: input.agent, status: input.status });
  taskDuration.observe({ agent: input.agent }, input.durationSeconds);
  // Do not log req.body or task details.
  return res.json({ recorded: true });
});

app.get('/metrics', async (_req, res) => {
  res.set('Content-Type', registry.contentType);
  res.send(await registry.metrics());
});

{
  "agent": "support-bot",
  "status": "succeeded",
  "durationSeconds": 12.4
}

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

Files

SKILL.md and 2 other files (references) in skills/.curated/lindy-observability of jeremylongshore/tons-of-skills-marketplace.

• SKILL.md
• references/implementation-guide.md
• references/implementation.md

Open the folder on GitHubat commit cfae287