plan-discussion

A command turns user input or a document into a structured GitHub Discussion, a conversation page attached to a GitHub repository. It supports decision records, design proposals, retrospectives, post-mortems, distribution analyses, and evaluations.

In plain words
What is it for?
It is for creating repository discussions from text or documents, detecting the repository, selecting a discussion type, and maintaining `docs/github-planner/KNOWLEDGE.md`.
Why use it?
It organizes unstructured notes into a consistent discussion format and keeps a knowledge file updated. It also checks whether the repository supports Discussions before continuing.

Command

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/anettodev/github-planner/plan-discussion
Clone the repo
git clone --depth 1 https://github.com/anettodev/github-planner
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 571 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 $0.00000 $0.00571
Opus 5 $0.00000 $0.00285
Sonnet 5 $0.00000 $0.00114
Haiku 4.5 $0.00000 $0.00057

Measured yesterday against content hash e3af6b6f31bb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

plan-discussion 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/commands/plan-discussion.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create GitHub Discussion

Create a structured GitHub Discussion from user input or a document. Maintains the Knowledge Manifest at docs/github-planner/KNOWLEDGE.md.

Arguments: $ARGUMENTS (optional — path to document, optional flags: --repo owner/repo, --type decision|design|retro|postmortem|distribution|analysis)

Steps

1. Detect Repository

  • If --repo flag provided, use that
  • Otherwise run gh repo view --json nameWithOwner -q .nameWithOwner
  • Verify Discussions are enabled: gh api repos/OWNER/REPO --jq '.has_discussions'
  • If Discussions are disabled, inform the user and stop

2. Determine Type

If --type flag provided, use that.

If a document path is provided, use the discussion-builder skill to infer the type from content signals.

Otherwise, ask the user:

What type of discussion?
  1. Decision (RFC)
  2. Design Proposal
  3. Sprint Retro
  4. Post-mortem
  5. Distribution Analysis
  6. Evaluation / Analysis

Wait for selection.

3. Gather Content

If document path provided:

  • Read the document
  • Use the discussion-builder skill to restructure it into the matching template
  • Ask the user to confirm or adjust the extracted content

If no document (interactive mode):

  • Use the discussion-builder skill's interview questions for the selected type
  • Ask each question and build the body from answers
  • For Distribution Analysis, ask the channel name first (user types freely)

4. Build Discussion

Using the gathered content:

  • Select the matching template from the discussion-builder skill's references/
  • Fill the template with the content
  • Resolve the Discussion category (list available categories, map to the best fit)
  • Identify related issues if mentioned

5. Present for Approval

Show the full discussion preview:

  • Title
  • Category
  • Body (rendered)
  • Related issues
  • Manifest entry that will be added

DO NOT create until user confirms.

6. Create Discussion

Launch the discussion-manager agent to:

  1. Create the GitHub Discussion
  2. Update docs/github-planner/KNOWLEDGE.md (create if first time)
  3. Archive old entries if manifest exceeds 20 KB
  4. Commit manifest changes

Read the full file on GitHub · 82 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 · 82 lines · 0 tokens per session scan A e3af6b6f31bb

Subscribe to this mod's changes

plan-discussion is a command published in the GitHub repository anettodev/github-planner (2 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 571 tokens. 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.