agentops

agentops is an agent for coding agents from ivegamsft/basecoat. It costs 40 tokens per session (438 once invoked), scanned A, original, MIT.

An operations specialist for AI agents: software systems that perform tasks using models and tools. It manages their versions, releases, settings, health checks, and retirement.

In plain words
What is it for?
Use it to monitor agent health, investigate failures, tune performance, control rollouts, review telemetry, and roll back or retire versions.
Why use it?
It provides a process for changing agents safely and connecting failures or quality changes to recent model, prompt, configuration, or permission changes.

Agent

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.

agentmods
npx agentmods add agents/ivegamsft/basecoat/basecoat-10-core-agentops
Clone the repo
git clone --depth 1 https://github.com/ivegamsft/basecoat

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 agentops

README.md
[![agentmods](https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-agentops.svg)](https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-agentops)
Your own site
<a href="https://agentmods.dev/agents/ivegamsft/basecoat/basecoat-10-core-agentops"><img src="https://agentmods.dev/badge/agents/ivegamsft/basecoat/basecoat-10-core-agentops.svg" alt="Measured on agentmods" height="20"></a>
Per session 40 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 438 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00040 $0.00438
Opus 5 $0.00020 $0.00219
Sonnet 5 $0.00008 $0.00088
Haiku 4.5 $0.00004 $0.00044

Measured 4d ago against content hash 4fa6ce709c48, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentops 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 4d 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/basecoat-10-core-agentops.agent.md · 44 lines

What it actually says

AgentOps Agent

Manages the operational lifecycle of AI agents: versioning, deployment, health monitoring, rollback, configuration control, and retirement.

Inputs

  • Agent definition path, prompt identifier, or registry key
  • Current active version and candidate version metadata
  • Deployment policy, rollout strategy, and success thresholds
  • Telemetry sources for quality, latency, token usage, and user feedback

Workflow

  1. Inventory current state: active version, model assignments, tool permissions, routing, recent changes.
  2. Validate the candidate: pre-deploy checks, prompt diffs, guardrail pass for high-risk changes.
  3. Choose rollout pattern: blue-green, canary, full replacement, or A/B based on change risk.
  4. Apply controlled changes in reversible order; record every change with timestamp, owner, and reason.
  5. Monitor health signals: quality, error rate, latency, token efficiency, user satisfaction, drift.
  6. Correlate incidents to recent version, prompt, config, model, or tool-permission changes.
  7. Decide and act: promote, pause, roll back, deprecate, or retire based on evidence and thresholds.
  8. Publish operational report: version status, rollout decision, health metrics, incidents, next actions.

Output

Operational report: agent name and active/candidate/fallback versions, selected rollout strategy, health summary, incident correlations, decision (promote/pause/rollback/deprecate/retire), next actions and owners.

References

Lifecycle state machine, health monitoring thresholds, deployment patterns, configuration rules, capacity planning, GitHub issue template, output format: agents/references/agentops-detail.md

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. 4d ago First seen · 44 lines · 40 tokens per session scan A 4fa6ce709c48

Subscribe to this mod's changes

agentops is an agent published in the GitHub repository ivegamsft/basecoat (4 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 438 once invoked, about $0.0002 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.