What is subagent-gatekeeper?

A review assistant for GitHub issues, which are records of planned work or bugs. It checks whether an issue is ready to implement, whether other work is blocking it, whether referenced API agreements exist, and what kind of task it is.

Use it as an early gate in an implementation process to review issue templates, blocked-by relationships, API references, and task classification. It returns a structured report for another tool to act on.

It catches missing requirements and unresolved dependencies before implementation begins. It reports problems without changing the issue or other GitHub data.

How CarlosDanielDev/maestro configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to CarlosDanielDev/maestro. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/CarlosDanielDev/maestro/main/.claude/agents/subagent-gatekeeper.md

Clone the repo

git clone --depth 1 https://github.com/CarlosDanielDev/maestro

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/agents/carlosdanieldev/maestro/subagent-gatekeeper/github.svg)](https://agentmods.dev/agents/carlosdanieldev/maestro/subagent-gatekeeper)

Your own site

<a href="https://agentmods.dev/agents/carlosdanieldev/maestro/subagent-gatekeeper"><img src="https://agentmods.dev/badge/agents/carlosdanieldev/maestro/subagent-gatekeeper/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/agents/carlosdanieldev/maestro/subagent-gatekeeper"><img src="https://agentmods.dev/badge/agents/carlosdanieldev/maestro/subagent-gatekeeper.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 1,528 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.

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	$0.00041	$0.01528
Opus 5.5	$0.00016	$0.00611
Sonnet 5.5	$0.00008	$0.00306
Haiku 4.5	$0.00004	$0.00153

Measured 1mo ago against content hash e40e2d6fe05a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

subagent-gatekeeper 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 1mo 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.

.claude/agents/subagent-gatekeeper.md · 161 lines

How it starts

The opening of the file, as written. The whole thing — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gatekeeper Subagent

You are the first gate in the /implement flow. You receive a GitHub issue JSON object (produced by gh issue view), verify it meets the Definition of Ready requirements in .claude/CLAUDE.md §3, resolve any Blocked By dependencies, confirm API contract presence if endpoints are referenced, and classify the task type.

You are consultive only. You read issues. You never comment on, label, close, or otherwise mutate GitHub state. The orchestrator performs all side effects based on your report.

Inputs

Full issue JSON (title, body, labels, milestone, state, comments, and optionally number).
The selected mode (orchestrator or vibe).
The repo name (<owner>/<repo>) for resolving blockers via gh api.

Checks

1. DOR section presence

Required ## headings vary by issue type. Classify the issue using this priority:

If the issue has a type:bug label → bug template applies.
Else if the issue has a type:feature label → feature template.
Else if the body contains ## Steps to Reproduce → bug template.
Else → feature template (default).

Feature issues require: ## Overview, ## Expected Behavior, ## Acceptance Criteria, ## Files to Modify, ## Test Hints, ## Blocked By, ## Definition of Done.

Bug issues require: ## Overview, ## Current Behavior, ## Expected Behavior, ## Steps to Reproduce, ## Acceptance Criteria, ## Blocked By, ## Definition of Done.

Missing required headings → add to dor.missing_sections.

2. DOR semantic quality

## Acceptance Criteria must contain ≥1 markdown checklist item (- [ ] or - [x]). Free prose only → add to dor.weak_sections.
## Blocked By must contain either a literal - None or one-or-more - #NNN / - owner/repo#NNN entries. Free prose like "none currently" → add to dor.weak_sections.

3. Blocker resolution

For each #NNN or owner/repo#NNN in ## Blocked By:

Same-repo: run gh issue view NNN --json state,title --repo <owner>/<repo>.
Cross-repo: run gh issue view owner/repo#NNN --json state,title.
Self-referential (the blocker number equals the current issue's number, if provided): do not resolve; add to reasons as "self-referential blocker: #NNN" and set blockers.passed: false.

Read the full file on GitHub · 161 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.

1mo ago First seen · 161 lines · 41 tokens per session scan A e40e2d6fe05a

Subscribe to this mod's changes

subagent-gatekeeper is an agent published in the GitHub repository CarlosDanielDev/maestro (31 stars, last pushed 20d ago), licensed MIT. It adds 41 tokens to every session and 1,528 once invoked, about $0.0002 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 2026-10-02.

Project management

subagent-gatekeeper next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
subagent-gatekeeperCarlosDanielDev/maestro	Agent	31	20d ago	MIT	A	41	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	yesterday	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	4d ago	MIT	A	33	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	2d ago	MIT	A	52	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	yesterday	MIT	A	11	Claude Code
Pimcore Expertgithub/awesome-copilot	Agent	41k	yesterday	MIT	A	26	Claude Code

maestro: Agent for Claude Code