discuss

A read-only discussion workflow for clarifying a feature, bug, or design question before implementation. It examines relevant source files when available, then surfaces assumptions or asks focused questions until there is a clear decision.

In plain words
What is it for?
Use it to explore an idea, compare design options, inspect related code, and agree on an explicit direction before creating a specification or plan.
Why use it?
It helps expose missing requirements and risky assumptions before code is written. Because it is read-only, it does not make implementation changes during the discussion.

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/shdennlin/agent-plugins/discuss
Any agent
npx skills add shdennlin/agent-plugins --skill discuss
Clone the repo
git clone --depth 1 https://github.com/shdennlin/agent-plugins

Made for: Claude Code, Codex.

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 909 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 $0.00054 $0.00909
Opus 5 $0.00027 $0.00454
Sonnet 5 $0.00011 $0.00182
Haiku 4.5 $0.00005 $0.00091

Measured yesterday against content hash 657a3d420abb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

discuss 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.

plugins/discuss/skills/discuss/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Discuss — Portable Framing

Have a focused, converging discussion about a topic. Thinking, not implementing: you may read files and search code, but NEVER write code or create files during this skill. If the user asks to implement, tell them to end the discussion first.

Input: the argument is the topic — a design question, a problem statement, a vague idea. If empty, ask what to discuss.

Step 1: Scout

Extract 2-5 keywords from the topic. Grep/Glob for related source files (not docs/tests). Read up to 5 of the most relevant. Spend seconds, not minutes.

Step 2: Pick a mode and announce it

  • 3+ related source files found → Assumptions mode. You have enough context to form opinions; list them and let the user correct.
  • Fewer → Interview mode. Ask questions one at a time.

Announce the choice: "Found a.ts, b.ts, c.rs — listing my assumptions." or "Didn't find much related code — I'll interview."

Assumptions mode

Present 3-5 assumptions. Each MUST include:

  1. Approach: what you'd do and why
  2. Evidence: file path(s) that informed it
  3. If wrong: the concrete consequence

Then ask exactly: "Which of these are wrong?" If all fine → converge. If corrected → one focused follow-up per correction, then converge.

Interview mode

  • ONE question per message. Skip anything already answered.
  • Prefer multiple choice with concrete options over open-ended.
  • When exploring approaches, present 2-3 options with a trade-off table and a recommendation — never a menu without an opinion.

Step 3: Discussion discipline (both modes)

  • Ground in reality — cite actual files, not theory.
  • Challenge assumptions — the user's and yours. Apply YAGNI; ask "do we need this?"
  • No empty validation — never "great question" / "that could work"; state why or why not.
  • Push for specifics — "make it more modular" is not an answer; ask what gets split, into what, at what cost.
  • Be direct — lead with your recommendation and the reason.
  • Respect pace — if the user pushes to move on, flag the single most important unresolved question in one sentence, then converge. One nudge maximum.

Read the full file on GitHub · 93 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 · 93 lines · 54 tokens per session scan A 657a3d420abb

Subscribe to this mod's changes

discuss is a skill published in the GitHub repository shdennlin/agent-plugins (2 stars, last pushed 8d ago), licensed MIT. It adds 54 tokens to every session and 909 once invoked, about $0.0003 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens