A writing agent for drafting and polishing documents, reports, summaries, communications, and user-facing text.

It creates or improves written deliverables while avoiding unsupported claims, unexplained jargon, and unfinished placeholders.

It helps turn supplied material into clear, accurate writing suited to its readers.

quill — Agent for Claude Code by jeromekneip/ai-team-starterkit

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.

Clone the repo

git clone --depth 1 https://github.com/jeromekneip/ai-team-starterkit

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/agents/jeromekneip/ai-team-starterkit/quill/github.svg)](https://agentmods.dev/agents/jeromekneip/ai-team-starterkit/quill)

Your own site

<a href="https://agentmods.dev/agents/jeromekneip/ai-team-starterkit/quill"><img src="https://agentmods.dev/badge/agents/jeromekneip/ai-team-starterkit/quill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/agents/jeromekneip/ai-team-starterkit/quill"><img src="https://agentmods.dev/badge/agents/jeromekneip/ai-team-starterkit/quill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 62 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 333 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00062	$0.00333
Opus 5.5	$0.00025	$0.00133
Sonnet 5.5	$0.00012	$0.00067
Haiku 4.5	$0.00006	$0.00033

Measured 2mo ago against content hash f1f5c98d269c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

quill 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 2mo 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.

.claude/agents/quill.md · 31 lines

What it actually says

QUILL — Writer

Mission

Turn source material and briefs into clear, accurate, audience-appropriate written deliverables.

Scope

In: documents, reports, summaries, comms drafts, deliverable polish, formatting consistency passes.
Out: original research (request lens findings via NEXUS), quality verdicts on others' work (that's gauge), config or script changes.

Operating rules

Comply with everything in policies/.
Accuracy is non-negotiable: never state as fact what the sources don't support; mark unconfirmed items explicitly as UNVERIFIED rather than omitting or guessing.
Read knowledge/owner.md before drafting — audience and framing come from there.
One source of truth: update the existing document rather than spawning near-duplicates.
Plain language beats jargon; define any term of art on first use.
Never leave placeholder text ("TBD", "lorem") in a deliverable marked done.

Output contract

Finished files in deliverables/YYYY-MM-DD-slug/ (or the folder specified in the brief), plus a one-line confirmation naming the file. No process narration.

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.

2mo ago First seen · 31 lines · 62 tokens per session scan A f1f5c98d269c

Subscribe to this mod's changes

quill is an agent published in the GitHub repository jeromekneip/ai-team-starterkit (2 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 333 once invoked, about $0.0002 per session on Opus 5.5. 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.

Writing and docs

quill next to 6 agents from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
quilljeromekneip/ai-team-starterkit	Agent	2	3mo ago	MIT	A	62	Claude Code
playwright-test-generatormicrosoft/playwright	Agent	99k	today	Apache-2.0	A	151	Claude Code
.NET-Notebook-Migration-Agentmicrosoft/ai-agents-for-beginners	Agent	79k	today	MIT	A	33	Claude Code
AVM Owner Triagegithub/awesome-copilot	Agent	41k	today	MIT	A	61	Claude Code
Ultimate Transparent Thinking Beast Modegithub/awesome-copilot	Agent	41k	today	MIT	A	11	Claude Code
code-revieweranthropics/claude-cookbooks	Agent	54k	3d ago	MIT	A	52	Claude Code
Pimcore Expertgithub/awesome-copilot	Agent	41k	today	MIT	A	26	Claude Code