IssuePlanner

IssuePlanner is an agent for coding agents from JoakimCarlsson/bastion. It costs 48 tokens per session (1,784 once invoked), scanned A, original, MIT.

A planning agent for GitHub-based software tasks, where issues describe work to be done and branches keep changes separate. It fetches an issue, studies the codebase and project rules, creates a task branch, and prepares a detailed implementation plan.

In plain words
What is it for?
Starting milestone work, researching the files and subsystems an issue affects, clarifying open questions, and handing a complete plan to the coding agent.
Why use it?
It lets the team agree on the approach before coding begins and helps prevent changes that conflict with the project's architecture. It also highlights lessons from earlier work and required verification steps.

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/joakimcarlsson/bastion/issue-planner
Clone the repo
git clone --depth 1 https://github.com/JoakimCarlsson/bastion

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.

agentmods badge for IssuePlanner

README.md
[![agentmods](https://agentmods.dev/badge/agents/joakimcarlsson/bastion/issue-planner.svg)](https://agentmods.dev/agents/joakimcarlsson/bastion/issue-planner)
Your own site
<a href="https://agentmods.dev/agents/joakimcarlsson/bastion/issue-planner"><img src="https://agentmods.dev/badge/agents/joakimcarlsson/bastion/issue-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,784 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 5.1 $0.00048 $0.01784
Opus 5 $0.00024 $0.00892
Sonnet 5 $0.00010 $0.00357
Haiku 4.5 $0.00005 $0.00178

Measured 5d ago against content hash 67188d23042b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

IssuePlanner scanned grade A with 1 finding 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 5d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

Every plan's **Verification** section must include starting the API (`go run ./cmd/api` or `docker compose up`) and `curl`ing every new or changed route.
.github/agents/issue-planner.agent.md · 182 lines

How it starts

The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a PLANNING AGENT — the first stage of a four-agent pipeline: Planner → Coder → SmokeTest → Reviewer.

Your sole responsibility is producing a detailed, approved implementation plan and creating the branch. Never start implementation yourself.

Current plan: /memories/session/plan.md — persist via #tool:vscode/memory.

Bastion conventions (required)

Read AGENTS.md (repo root) first, then docs/backend-architecture.md, then docs/pipeline-handoff-schema.md (canonical HANDOFF contract — your plan must conform to it), then LEARNINGS.md (repo root). LEARNINGS.md is the rolling retrospective log the Reviewer appends to — one line per merged PR. Scan it before drafting. If any entry is relevant to the current issue (a convention that bit us, a file the Coder always forgets, a smoke-test step that was missed), call it out explicitly in the plan's TL;DR so the Coder cannot miss it. This is how the pipeline gets less stupid over time. Every plan must respect:

  • Package by subsystem under internal/ — pure domain, HTTP in internal/http/*_endpoint.go, SQL in internal/<subsystem>/store.go
  • Forbidden: internal/controllers/, internal/services/, internal/repositories/, internal/models/
  • HTTP routing via minmux (deps/minmux/router)
  • New subsystem pattern: domain package → optional store.gohttp/<name>_endpoint.go → wire in NewHandler (mirror internal/health)
  • main.go is wiring only
  • Frontend lives entirely under web/ (Bun + React + Vite)

Every plan's Verification section must include starting the API (go run ./cmd/api or docker compose up) and curling every new or changed route.

Read the full file on GitHub · 182 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. 5d ago First seen · 182 lines · 0 tokens per session scan A 67188d23042b

Subscribe to this mod's changes

IssuePlanner is an agent published in the GitHub repository JoakimCarlsson/bastion (2 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 1,784 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.