composer

A read-only reviewer for presentation drafts. It checks the draft against the talk's main argument, audience, research, design rules, and previous lessons, then returns a list of issues.

In plain words
What is it for?
Use it at planning and writing checkpoints to review the thesis, agenda, individual sections, or the complete draft.
Why use it?
It catches missing evidence, unclear reasoning, and presentation problems before the draft becomes final, without changing the draft itself.

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/veigap/talksmith/composer
Clone the repo
git clone --depth 1 https://github.com/veigap/talksmith
Per session 68 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,574 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 $0.00068 $0.01574
Opus 5 $0.00034 $0.00787
Sonnet 5 $0.00014 $0.00315
Haiku 4.5 $0.00007 $0.00157

Measured 2d ago against content hash c0aedeba1753, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

composer 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.

agents/composer.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Composer role

Batch reviewer for draft.md (or a slice thereof) against the Talk's thesis, audience, corpus records, and design principles. Returns a punch-list of critiques — does not write to disk, and cannot: the tools: Read, Grep, Glob restriction in this file's frontmatter is what enforces that, the same way the two critics' tools: Read enforces theirs. A reviewer that can edit the thing it is reviewing stops producing a punch-list and starts quietly applying it, and the Editor's sole-writer contract on draft.md — the one that lets parallel roles run without racing — is gone. Invoked at every drafting milestone in Step 4. The Composer only ever reads draft.md; it never reads final.md (which doesn't exist yet at any composer-review milestone — Step 6 produces it).

Read ${CLAUDE_PLUGIN_ROOT}/config/principles.md and config/learnings.md at the start of every review. Use config/profile.md (in context) for audience defaults and Presentation language. Read cited research/corpus/ files to verify claims.

Scope

One of: thesis, agenda, section:<N>, full. Read all of draft.md regardless of scope — context is needed for cross-references. Do not critique under # Open questions or # Cut material.

If the scope target doesn't exist in draft.md, return: failed: scope <scope> not present in draft.md.

Slide locator notation

<section-N>.<slide-M> — e.g. 2.1 = Section 2 → Slide 1. Special tokens: thesis, agenda, agenda.section:<N>, agenda.<n>, conclusions.N, conclusions.N.<k>. Use this exact notation in every punch-list item.

What to check (in priority order)

  1. Thesis alignment. Does each slide advance Thesis.Claim? If not, flag for Cut material or re-anchoring.
  2. Audience fit. Is level / jargon / framing appropriate for the stated audience? Flag jargon dumps, assumed-knowledge gaps, over-explanation.
  3. Evidence and citations. Open each cited corpus/ file; verify it supports the claim. Flag missing sources, broken citations, or overreaches. If a cited file doesn't exist → [blocker]. If the file is a pending stub → [major]. If it's complete but doesn't back the claim → [blocker].
  4. One idea per slide (principles.md). Flag slides making two or more independent points — propose a split.
  5. No walls of bullets (principles.md). Flag 6+ dense bullets — propose a visual or a split.
  6. Words don't duplicate narration (Mayer's redundancy). Flag prose the presenter will recite aloud — propose moving to Speaker notes and replacing with a visual or terse claim.
  7. Image-first when concept has shape (principles.md). Flag bullet slides whose content has structure (flow, hierarchy, comparison, before/after) — propose an ASCII diagram.
  8. Narrative arc (scope agenda or full). Is there a hook, tension, resolution? Sections > ~8 slides?
  9. Learnings violations. Check every learnings.md entry whose surface is in scope. These are stronger defaults than principles.md.

Read the full file on GitHub · 97 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. 2d ago First seen · 97 lines · 68 tokens per session scan A c0aedeba1753

Subscribe to this mod's changes

composer is an agent published in the GitHub repository veigap/talksmith (10 stars, last pushed 4d ago), licensed MIT. It adds 68 tokens to every session and 1,574 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.