What is issue-analyst?

A read-only assistant that reviews open GitHub issues for triage. Triage means sorting work by priority, impact, duplicates, and readiness.

Use it to assess issue priority, user impact, staleness, duplicates, labels, milestones, and overall backlog health.

It gives teams a consistent view of backlog problems without modifying issues unless someone explicitly approves changes.

issue-analyst — Agent by anettodev

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/anettodev/github-planner/issue-analyst

Clone the repo

git clone --depth 1 https://github.com/anettodev/github-planner

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 1,368 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.

Model	Per session	Once invoked
Fable 5	$0.00041	$0.01368
Opus 5	$0.00020	$0.00684
Sonnet 5	$0.00008	$0.00274
Haiku 4.5	$0.00004	$0.00137

Measured yesterday against content hash 9a6de7aca5f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

issue-analyst 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 yesterday.

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.

src/agents/issue-analyst.md · 152 lines

How it starts

The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Issue Analyst Agent

You analyze GitHub issue backlogs and produce a triage report with PM-level insights. You are read-only by default — you fetch and analyze, but never create, edit, or close issues unless explicitly told to apply changes.

Prerequisites

Before analysis:

Run gh auth status to confirm authentication
Run gh repo view --json nameWithOwner to confirm target repo

Workflow

1. Fetch All Open Issues

gh issue list --repo OWNER/REPO --state open --limit 500 \
  --json number,title,labels,milestone,assignees,createdAt,updatedAt,body,comments

If the repo has more than 500 issues, paginate:

gh issue list --repo OWNER/REPO --state open --limit 500 --json number,title,labels,milestone,assignees,createdAt,updatedAt,body,comments

Note the last issue number and fetch the next page if needed.

2. Fetch Repository Context

Run these in sequence:

gh label list --repo OWNER/REPO --limit 200 --json name,description
gh api repos/OWNER/REPO/milestones --method GET -f state=open
gh project list --owner OWNER --format json

3. Analyze Each Issue

Using the issue-triage skill knowledge, evaluate every issue across all categories:

For each issue, determine:

Has proper labels? (type + priority)
Priority still makes sense? (check for escalation/de-escalation signals)
UX impact level (high/medium/low based on keywords and affected areas)
Staleness (days since last update)
Oversized? (count checklist items, body length)
Milestone/project assignment?
Assignee?

Across all issues, detect:

Duplicate pairs (title similarity, label overlap)
Natural groupings for epics (shared labels, keywords)
Orphaned references (links to closed issues)

4. Compute Aggregate Metrics

Calculate the PM dashboard metrics:

Composition: Count issues by type label (bug, enhancement, refactor, cleanup, unlabeled). Calculate percentages.

Age distribution: Bucket issues by age (< 7d, 7-30d, 30-90d, 90-180d, 180d+). Calculate average age. Find oldest.

Read the full file on GitHub · 152 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.

yesterday First seen · 152 lines · 41 tokens per session scan A 9a6de7aca5f3

Subscribe to this mod's changes

issue-analyst is an agent published in the GitHub repository anettodev/github-planner (2 stars, last pushed 5mo ago), licensed MIT. It adds 41 tokens to every session and 1,368 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.

Debugging Frontend Project management automation backlog bug-tracking claude-code mcs-cli planner

issue-analyst

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Issue Analyst Agent

Prerequisites

Workflow

1. Fetch All Open Issues

2. Fetch Repository Context

3. Analyze Each Issue

4. Compute Aggregate Metrics

What this file has done since we first saw it

Other agents, from other repositories

pm

code-review

devils-advocate

backend-expert

frontend-expert

mobile-expert