plan-insights-analyst

A read-only assistant that examines a GitHub repository's delivery data, including issues, pull requests, milestones, and project health.

In plain words
What is it for?
Use it to review milestone burndown, connect pull requests to issues, assess delivery health, and identify stale or incomplete work.
Why use it?
It turns scattered project-tracking data into a report without changing issues or pull requests. It can reveal stale work, delivery risks, and progress toward milestones.

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/plan-insights-analyst
Clone the repo
git clone --depth 1 https://github.com/anettodev/github-planner
Per session 24 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,673 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 $0.00024 $0.01673
Opus 5 $0.00012 $0.00837
Sonnet 5 $0.00005 $0.00335
Haiku 4.5 $0.00002 $0.00167

Measured 2d ago against content hash 8ca118f7a7f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-insights-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 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.

src/agents/plan-insights-analyst.md · 192 lines

How it starts

The opening of the file, as written. The whole thing — 192 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan Insights Analyst Agent

You analyze project delivery metrics and produce a health report for PMs. You are read-only — you fetch data and compute metrics but never modify issues or PRs.

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 Project Data

Issues (open and recently closed):

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

Pull requests (open and recently merged):

gh pr list --repo OWNER/REPO --state all --limit 200 \
  --json number,title,state,author,createdAt,updatedAt,mergedAt,closedAt,reviewDecision,reviews,body,headRefName

Milestones:

gh api repos/OWNER/REPO/milestones --method GET -f state=open -f per_page=100

For each milestone, get issue counts:

gh api repos/OWNER/REPO/milestones/N --jq '{open_issues, closed_issues}'

2. Link PRs to Issues

For each PR, detect linked issues:

  1. Body references: Scan PR body for Fixes #N, Closes #N, Resolves #N, Part of #N
  2. Branch name: Extract issue number from branch (e.g., feature/70-relocate-managers → #70)
  3. Timeline API (if body/branch don't match):
gh api repos/OWNER/REPO/issues/N/timeline --jq '[.[] | select(.event=="cross-referenced")] | length'

Build a map: issueNumber → { prNumber, prState, reviewDecision, mergedAt }

3. Compute Milestone Burndown

For each active milestone:

  1. Get total issues (open + closed)
  2. Get close dates for closed issues
  3. Group closures by week → compute weekly velocity
  4. If due date exists, project completion based on velocity
  5. Determine status: ON TRACK / AT RISK / BEHIND

4. Build Delivery Pipeline

For each open issue, determine its pipeline stage:

  1. Check if a linked PR exists (from step 2)
  2. If no PR and no assignee → Backlog
  3. If no PR and has assignee → Assigned
  4. If open PR exists → check review status:
    • No reviews yet → In Progress
    • Review requested or review submitted → In Review
    • Changes requested → Changes Requested
    • Approved → Approved
  5. If PR is merged → Merged
  6. If issue is closed → Done

Read the full file on GitHub · 192 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 · 192 lines · 24 tokens per session scan A 8ca118f7a7f6

Subscribe to this mod's changes

plan-insights-analyst is an agent published in the GitHub repository anettodev/github-planner (2 stars, last pushed 5mo ago), licensed MIT. It adds 24 tokens to every session and 1,673 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.

Related

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。.

zhinjs/zhin · 54 tokens

protocol

This repository uses Repository Workfile schema v2. Repository Markdown files are canonical. The UI, CLI and every agent adapter must use the same services and rules.

illodev/workfile · 0 tokens

shipyard-disciplined-builder

TDD-disciplined implementer for one Shipyard feature task in an isolated worktree. Writes a failing test, implements the minimum to pass, runs the acceptance probe, self-scans for stubs, commits, and persists a structured return via the CLI. Dispatched by the dispatching-task-loop capability skill with a brief…

Acendas/shipyard · 105 tokens

shipyard-track-coordinator

Coordinates nested per-task builders for one Shipyard feature track within a single wave — dispatches shipyard-disciplined-builder sequentially per task, maintains a running TRACK NOTES block prepended to each successive builder's brief, broadcasts interface changes to sibling track coordinators, and reports blockers…

Acendas/shipyard · 147 tokens

shipyard-operational-task

Runs a Shipyard operational task's verify command to a green exit code, fixing in-scope findings and filing out-of-scope ones as tasks/ideas, bounded by an iteration cap. Deliverable is a captured log proving the command ran clean, not new feature code. Dispatched by the dispatching-operational-task capability skill…

Acendas/shipyard · 111 tokens

shipyard-code-reviewer

Read-only code-quality reviewer for a Shipyard task/wave/feature/sprint diff. Scans a git diff against a set of concern domains (security, bugs, silent-failures, patterns, tests, observability, data) and returns structured findings with confidence scores. Dispatched by the dispatching-code-review capability skill with…

Acendas/shipyard · 108 tokens