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.
npx agentmods add agents/anettodev/github-planner/dev360-analystgit clone --depth 1 https://github.com/anettodev/github-plannerWhat 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 | $0.00029 | $0.01218 |
| Opus 5 | $0.00015 | $0.00609 |
| Sonnet 5 | $0.00006 | $0.00244 |
| Haiku 4.5 | $0.00003 | $0.00122 |
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.
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:
- Run
gh auth statusto confirm authentication - Run
gh repo view --json nameWithOwnerto 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?
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 · 142 lines · 29 tokens per session scan A 8673c567ae79
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.
Other agents, from other repositories
pm
产品经理(PM)角色:负责需求分析、Issue 拆分与优先级管理、Sprint 规划、 跨角色协调与验收。监听 issues.opened 事件,自动评审需求并拆分为可执行任务。.
code-review
Bu agent Agentbase den spawn olur ve ../Codebase/ uzerinde calisir.
devils-advocate
Bu agent Agentbase den spawn olur ve ../Codebase/ uzerinde calisir.
backend-expert
Bu agent Agentbase den spawn olur ve ../Codebase/ uzerinde calisir.
frontend-expert
Bu agent Agentbase den spawn olur ve ../Codebase/ uzerinde calisir.
mobile-expert
Bu agent Agentbase den spawn olur ve ../Codebase/ uzerinde calisir.