discussion-builder

A guide for turning notes or planning documents into structured GitHub Discussions, which are conversation pages attached to a repository.

In plain words
What is it for?
Use it to prepare discussions about technical choices, designs, sprint lessons, incidents, distribution channels, or evaluations of tools and vendors.
Why use it?
It helps teams choose a suitable discussion format and organize the information needed for a useful decision, proposal, retrospective, post-mortem, or analysis.

Skill for Claude CodeCodex

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 skills/anettodev/github-planner/discussion-builder
Any agent
npx skills add anettodev/github-planner --skill discussion-builder
Clone the repo
git clone --depth 1 https://github.com/anettodev/github-planner

Made for: Claude Code, Codex.

Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,534 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 $0.01534
Opus 5 $0.00000 $0.00767
Sonnet 5 $0.00000 $0.00307
Haiku 4.5 $0.00000 $0.00153

Measured 2d ago against content hash 15fd20b719a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

discussion-builder 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/skills/discussion-builder/SKILL.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Discussion Builder Skill

You are an expert at creating structured GitHub Discussions from user input or planning documents. You interview the user, select the right template, and produce well-structured content for the discussion-manager agent to publish.

Discussion Types

Type Slug When to use
Decision (RFC) decision Team needs to choose between approaches
Design Proposal design Proposing architecture or technical approach
Sprint Retro retro End-of-sprint/phase reflection
Post-mortem postmortem Something went wrong, document lessons
Distribution Analysis distribution Analyze any distribution channel (App Store, Google Play, web, TestFlight, enterprise)
Evaluation / Analysis analysis Evaluate an SDK, tool, vendor, platform, or process

Type Detection

When a document path is provided, infer the type from content signals:

Signal Type
"options", "alternatives", "trade-off", "should we", "choose" decision
"proposal", "architecture", "design", "approach", "RFC" design
"retro", "went well", "improve", "action items", "sprint" retro
"incident", "root cause", "timeline", "outage", "broke" postmortem
"ratings", "reviews", "store", "downloads", "feedback", "crash rate" distribution
"SDK", "library", "dependency", "evaluate", "compare", "assessment", "vendor", "tool" analysis

If ambiguous, ask the user.

Interview Questions (interactive mode)

When no document is provided, ask targeted questions based on the selected type.

Decision (RFC)

  1. What needs to be decided? (title)
  2. What's the context? (why does this need a decision now?)
  3. What options are you considering? (at least 2)
  4. What are the constraints? (time, tech, team, cost)
  5. Which issues are related? (issue numbers)
  6. Who should weigh in? (GitHub usernames)
  7. When does this need to be decided by? (deadline)

Design Proposal

  1. What are you proposing? (title)
  2. What problem does this solve?
  3. How does it work? (high-level approach)
  4. What alternatives did you consider?
  5. What's the impact on existing code?
  6. Which issues does this relate to?

Read the full file on GitHub · 169 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 169 lines · 0 tokens per session scan A 15fd20b719a0

Subscribe to this mod's changes

discussion-builder is a skill 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 1,534 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.

Related

Other skills, from other repositories

backfill-enumerate-drain

How to backfill a newly-added repo or team — the enumerate-then-drain loop, the single-event contract, and resume-safe todo discipline. Load this when handling a .added seed event with the planner on.

potpie-ai/potpie · 52 tokens

summarize-assessment

Use after the napkinmath pipeline has produced parameters/bounds/scenarios/montecarlo JSON to generate a plan assessment (assessment.md) — a thin interpretation layer over the intermediary artifacts. Emits a JSON manifest, a provenance map, gate verdicts (Critical / Fragile / Marginal / Robust), failure drivers…

PlanExeOrg/PlanExe · 104 tokens

generate-bounds

Use when the user wants to generate low/base/high assumption ranges (bounds) for missing or uncertain variables in a validated extract-parameters-from-full JSON, in preparation for deterministic scenarios or Monte Carlo.

PlanExeOrg/PlanExe · 42 tokens

monte-carlo

Use when the user wants Monte Carlo simulation of a PlanExe model — sampling from bounds to produce output distributions (mean/std/percentiles), threshold pass probabilities, and Pearson-correlation sensitivity rankings — given an extract-parameters-from-full JSON, a generate-bounds JSON, a generate-calculations…

PlanExeOrg/PlanExe · 71 tokens

planexe-mcp

OpenClaw skill for connecting to PlanExe via Model Context Protocol. Supports three deployment scenarios: cloud-hosted service, remote Docker, and local Docker.

PlanExeOrg/PlanExe · 36 tokens

generate-calculations

Use when the user wants to turn a validated extract-parameters-from-full JSON into a Python module of deterministic functions implementing the formulahint expressions for downstream scenario runs and Monte Carlo.

PlanExeOrg/PlanExe · 39 tokens