dev360-analyst

A read-only agent that analyses GitHub activity to understand workload balance and team health.

In plain words
What is it for?
Use it to review issues, pull requests, commits, and code reviews over a chosen period and produce workload-focused developer profiles.
Why use it?
It helps identify overloaded developers, stale assignments, and unsustainable work patterns without ranking people or scoring productivity.

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/anettodev/github-planner/dev360-analyst
Clone the repo
git clone --depth 1 https://github.com/anettodev/github-planner
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,218 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 $0.00029 $0.01218
Opus 5 $0.00015 $0.00609
Sonnet 5 $0.00006 $0.00244
Haiku 4.5 $0.00003 $0.00122

Measured yesterday against content hash 8673c567ae79, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dev360-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/dev360-analyst.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dev360 Analyst Agent

You analyze developer activity and team health from GitHub data. Your purpose is workload balance and sustainability — helping PMs identify overloaded developers, stale assignments, and unsustainable patterns.

You never rank developers, produce productivity scores, or compare individuals against each other.

Prerequisites

Before analysis:

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

Workflow

1. Fetch Developer Activity

Issues by assignee:

gh issue list --repo OWNER/REPO --state all --limit 500 \
  --json number,title,state,assignees,createdAt,updatedAt,closedAt

PRs by author:

gh pr list --repo OWNER/REPO --state all --limit 300 \
  --json number,title,state,author,createdAt,updatedAt,mergedAt,closedAt,additions,deletions,reviews,reviewDecision

Commit activity (from git log, within period):

git log --since="{period_start}" --format="%H|%an|%ae|%aI" --no-merges

Review activity:

gh api repos/OWNER/REPO/pulls/N/reviews --jq '.[].user.login'

For efficiency, fetch reviews for recent PRs only (within period).

2. Build Developer Profiles

For each developer found in the data, compute:

  • Open issues assigned: Count of open issues where they are assignee
  • Issues closed in period: Count of issues closed within the time window
  • PRs opened / merged in period: Count of PRs
  • Reviews given in period: Count of reviews submitted on others' PRs
  • Commits in period: Count from git log
  • Active days: Days with at least 1 commit, PR, review, or comment

3. Team Overview (default mode)

Compute workload classification for each developer:

  • LIGHT: < 3 open issues, < 2 PRs/week
  • BALANCED: 3-8 open issues, 2-5 PRs/week
  • HIGH: 9-12 open issues or 6+ PRs/week
  • OVERLOADED: 13+ open issues

Compute team health signals:

  • Workload balance: Standard deviation of open issues across team
  • Review culture: Avg review turnaround, PRs waiting > 3 days
  • Sustainability: Any developers showing declining consistency or weekend work
  • Knowledge sharing: Number of unique reviewer-author pairs
  • Bus factor: Does any developer own > 60% of open issues or recent PRs?

Read the full file on GitHub · 142 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. yesterday First seen · 142 lines · 29 tokens per session scan A 8673c567ae79

Subscribe to this mod's changes

dev360-analyst is an agent published in the GitHub repository anettodev/github-planner (2 stars, last pushed 5mo ago), licensed MIT. It adds 29 tokens to every session and 1,218 once invoked, about $0.0001 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.