A production-monitoring workflow that reads telemetry, finds unusual behavior, determines whether it is a bug, and sends each finding to the appropriate next step. Telemetry means operational logs and measurements from a running system.

Use it after deployment, on a schedule, or when something looks wrong in a live system.

It turns production signals into an assigned response instead of leaving anomalies for someone to investigate manually. It can route bugs for fixing, change requests for triage, and infrastructure issues to operations.

aid-monitor — Skill for Claude Code by AndreVianna/aid-methodology

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add AndreVianna/aid-methodology --skill aid-monitor

Clone the repo

git clone --depth 1 https://github.com/AndreVianna/aid-methodology

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-monitor/github.svg)](https://agentmods.dev/skills/andrevianna/aid-methodology/aid-monitor)

Your own site

<a href="https://agentmods.dev/skills/andrevianna/aid-methodology/aid-monitor"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-monitor/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/andrevianna/aid-methodology/aid-monitor"><img src="https://agentmods.dev/badge/skills/andrevianna/aid-methodology/aid-monitor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,126 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. Third-party audits

NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00086	$0.03126
Opus 5.5	$0.00034	$0.01250
Sonnet 5.5	$0.00017	$0.00625
Haiku 4.5	$0.00009	$0.00313

Measured 26d ago against content hash 6d6d88b0d430, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

aid-monitor 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 26d 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.

.agents/skills/aid-monitor/SKILL.md · 262 lines

How it starts

The opening of the file, as written. The whole thing — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Observe, Classify, Act

State machine: OBSERVE → CLASSIFY → ROUTE → DONE.

Monitor production. Detect what's wrong. Route it to where it gets fixed.

Agents Involved

Default executor: aid-orchestrator (routes findings; never implements directly).
Telemetry interpretation: aid-researcher (reads logs/metrics, classifies anomalies).
Routing targets:
- BUG → /aid-fix (creates + implements the fix work).
- Change Request → /aid-triage (routes to the right entry).
- Infrastructure → escalated to ops (outside AID scope).

Argument-Hint

/aid-monitor work-NNN
/aid-monitor "<free-form description of what to observe>"

Two invocation modes (invocation-context detection; see ## ⚠️ Pre-flight Checks Step 0):

work-NNN present -- the existing pipeline path below runs unchanged (OBSERVE -> CLASSIFY -> ROUTE -> DONE, post-deployment). Required: work ID. If only one work exists, auto-select it.

Optional flags (this mode only):
- --since "YYYY-MM-DD" — observation window start (default: last deploy or last monitor run)
- --package package-NNN — scope to a specific deployment package
No work-NNN, a free-form description instead -- the Lite-path direct-entry shortcut: binds {name}=aid-monitor, {verb}=monitor, {artifact}="" (bare verb), {description}=<the given text>, then delegates to the shared shortcut engine (.aid/runtime/templates/shortcut-engine.md, INTAKE -> ... -> APPROVAL-HALT), scaffolding a flattened Lite work and running the grading gates. Never executes -- it halts for approval; this shortcut entry does not replace the pipeline role below, it adds a second, independent entry point to the same skill directory.

Workspace

.aid/works/{work}/
  packages/                    ← deployment history
  features/                    ← SPECs (expected behavior)
  deliveries/delivery-NNN/tasks/task-NNN/  ← full path: task files (acceptance criteria)
  tasks/task-NNN/                          ← lite path: task files (acceptance criteria; no delivery-NNN/ nesting)
  known-issues.md              ← known problems

Read the full file on GitHub · 262 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

26d ago Changed 6d6d88b0d430
1mo ago Changed 115e34b5cd3e
2mo ago First seen · 262 lines · 86 tokens per session scan A 7ddb1ce9d9ce

Subscribe to this mod's changes

aid-monitor is a skill published in the GitHub repository AndreVianna/aid-methodology (6 stars, last pushed 11d ago), licensed MIT. It adds 86 tokens to every session and 3,126 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.

Analytics and metrics Debugging

aid-monitor next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
aid-monitorAndreVianna/aid-methodology	Skill	6	11d ago	MIT	A	86	Claude Code
systematic-debuggingopen-metadata/OpenMetadata	Skill	16k	today	Apache-2.0	A	37	Claude Code
log-error-digestzebbern/claude-code-guide	Skill	4.7k	yesterday	MIT	A	71	Claude Code, Codex
cwv-optimizeradobe/skills	Skill	320	today	Apache-2.0	A	112	Claude Code
ci-fixersipyourdrink-ltd/bernstein	Skill	1.2k	yesterday	Apache-2.0	A	15	Claude Code, Codex
incident-response-incident-responsermyndharis/antigravity-skills	Skill	2.0k	24d ago	MIT	A	36	Claude Code
diagnosing-missing-recordingsPostHog/posthog	Skill	41k	today	none	A	76	Claude Code, Codex