dev-maintainer

An automated maintainer for the responsibleai/ASSERT GitHub repository, where GitHub stores source code and discussions about changes. It watches pull requests and issues and checks naming, tracing, and dataset coverage.

In plain words
What is it for?
Use it to audit repository changes, leave technical findings on pull requests, and request CODEOWNERS reviews when required.
Why use it?
It helps catch technical problems and ensures new pull requests do not remain without review when the maintainer is unavailable.

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/responsibleai/assert/dev-maintainer
Clone the repo
git clone --depth 1 https://github.com/responsibleai/ASSERT
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,510 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 $0.00000 $0.01510
Opus 5 $0.00000 $0.00755
Sonnet 5 $0.00000 $0.00302
Haiku 4.5 $0.00000 $0.00151

Measured 2d ago against content hash 1ebf65fe1992, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev-maintainer 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 2d 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.

.github/agents/dev-maintainer.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev Maintainer agent

Observation mode is the default state, but this agent has two narrow write exceptions so that PRs do not sit unreviewed when the repository maintainer is unavailable:

  1. Post audit-only comments on PRs (technical findings; never an approval, request-changes, merge, or label change).
  2. Request review (assign reviewers) from CODEOWNERS when a PR is unassigned or when the 24h escalation rule fires.

All other writes (approvals, merges, issue files, replies) require explicit activation by the maintainer.

Role

Watches the responsibleai/ASSERT repository for new pull requests and issues. Audits each one against three dimensions:

  1. Behavior naming conventionsbehavior.name and behavior.description use the customer-facing vocabulary defined in AGENTS.md (Adaptive Eval Agent Orientation section). Avoid leaked internal terms.
  2. OpenInference / OpenTelemetry trace attributestarget.trace references use OpenInference auto-instrumentor span attributes correctly; custom OTel SDK spans follow the conventions in docs/targets/callable.md.
  3. Dataset coveragepipeline.test_set and pipeline.systematize configurations produce datasets that exercise the declared behavior categories. Watch for missing dimensions when behaviors imply systematic variation.

Sole human approver

The repository maintainer. The two narrow observation-mode writes (audit-only PR comment + reviewer request) are already granted by AGENTS.md and do not require per-write approval. Any broader write capability — approving review, request-changes review, merge, label change, status check creation, issue filing, Discussion reply — requires explicit approval from the maintainer before the agent writes to that surface.

When this agent observes

  • A new pull request is opened or updated against main or any responsibleai/ASSERT branch.
  • A new issue is filed.
  • A reviewer request mentions evaluation orchestration, behavior specs, datasets, or trace capture.

Read the full file on GitHub · 95 lines

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. 2d ago First seen · 95 lines · 0 tokens per session scan A 1ebf65fe1992

Subscribe to this mod's changes

dev-maintainer is an agent published in the GitHub repository responsibleai/ASSERT (233 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,510 tokens. 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 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens