plan

A sprint-planning command that turns research notes into executable plan files, shared context, and feature acceptance checks. A sprint is a defined period of work focused on a set of tasks.

In plain words
What is it for?
Use it after sprint research to create one or more wave plans, record decisions, and define how each feature will be accepted.
Why use it?
It converts research into an ordered implementation plan and exposes unclear decisions before coding starts. It also checks the plans for problems and can create a GitHub issue.

Command

Part of the jira plugin — 13 commands, 9 agents shipped together

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 commands/koolamusic/claudefiles/plan
Clone the repo
git clone --depth 1 https://github.com/koolamusic/claudefiles

Or install jira, the plugin that ships this one along with the rest of its 13 commands, 9 agents.

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 1,259 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 $0.00048 $0.01259
Opus 5 $0.00024 $0.00629
Sonnet 5 $0.00010 $0.00252
Haiku 4.5 $0.00005 $0.00126

Measured 3d ago against content hash 5197fa219bb0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan 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 3d 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.

plugins/jira/commands/plan.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Convert the active sprint's RESEARCH.md into one or more executable PLAN files (one per wave-plan), plus CONTEXT.md.

Parse the input

$ARGUMENTS may include --push-issue. No other flags.

Steps

  1. Locate the active sprint: slug=$(cat .jira/CURRENT). If empty or missing, stop — there's no active sprint to plan.

  2. Verify inputs exist:

    • .jira/sprints/<slug>/BRIEF.md
    • .jira/sprints/<slug>/RESEARCH.md

    If either missing, stop and tell the user to run /jira:research first.

  3. First pass — spawn jira-planner:

    • Sprint slug
    • Brief path, research path
    • Context path: .jira/sprints/<slug>/CONTEXT.md (may not exist; planner creates it)
    • Plan output dir: .jira/sprints/<slug>/
    • References: PLAN template + CONTEXT template + feature template (templates/sprint/feature.feature)

    The planner writes features/*.feature (the sprint's acceptance predicates, @req:<ID> tagged) before the plans; plans claim predicates via effects: frontmatter.

    The planner may use AskUserQuestion (≤ 4 questions, bundled) for load-bearing ambiguity. Answers become CONTEXT.md decisions (D-XX).

  4. Handle planner return. One of:

    • ## PLANNING COMPLETE — proceed to step 5.
    • ## ⚠ Source Audit: Unplanned Items Found — surface the gap list via AskUserQuestion. Three options: A) re-spawn planner with instruction to add covering plans, B) split sprint, C) defer items to CONTEXT.md ## Deferred ideas. Then proceed.
    • ## SPRINT SPLIT RECOMMENDED — surface the proposal via AskUserQuestion. If user accepts, create the sub-sprint dirs and re-route to research. If user proceeds anyway, re-spawn planner with "force-fit" instruction.
  5. Audit pass — spawn jira-plan-checker with all *-PLAN.md paths + features/*.feature paths + brief + research + context. Returns a YAML block with verdict, issue_count, findings, required_revisions.

  6. Stall-aware revision loop (max 2 iterations):

    • Track prev_issue_count (initialized to ∞ before the first audit).
    • If verdict: REVISE:
      • If issue_count >= prev_issue_count: stalled — surface findings via AskUserQuestion with options: A) proceed-with-issues, B) re-spawn planner with explicit guidance, C) abandon. Exit if A or C.
      • Otherwise: re-spawn jira-planner with required_revisions appended. Re-audit. Set prev_issue_count = issue_count.
      • At most 2 iterations. After the second audit if still REVISE: surface findings, ask the user to accept-as-is / manually-edit / abandon.

Read the full file on GitHub · 89 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. 3d ago First seen · 89 lines · 48 tokens per session scan A 5197fa219bb0

Subscribe to this mod's changes

plan is a command published in the GitHub repository koolamusic/claudefiles (132 stars, last pushed 4d ago), licensed MIT. It adds 48 tokens to every session and 1,259 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 2026-08-30.