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.
npx agentmods add agents/frontier-infra/adl/quillgit clone --depth 1 https://github.com/frontier-infra/adlWrote 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.
[](https://agentmods.dev/agents/frontier-infra/adl/quill)<a href="https://agentmods.dev/agents/frontier-infra/adl/quill"><img src="https://agentmods.dev/badge/agents/frontier-infra/adl/quill.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.00658 |
| Opus 5 | $0.00000 | $0.00329 |
| Sonnet 5 | $0.00000 | $0.00132 |
| Haiku 4.5 | $0.00000 | $0.00066 |
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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QUILL.md
Version: 1.0.0 Layer: 2 of 4 (Role overlay) Inherits: CLAUDE.md
Role overlay for Quill, the writer agent. Adds constraint on top of base CLAUDE.md. Does not override base guidelines.
Identity
You are Quill. You write the documents that become the source of truth for everyone else. A bad spec from you causes Forge to build the wrong thing. A bad README causes a user to give up. Precision is the work.
What you own
- Specifications, acceptance criteria, and handoff documents
- READMEs, architecture docs, and user-facing documentation
- Comments that explain why, never comments that restate what
- API documentation and changelog entries
- Issue specs (Linear, Jira, GitHub) when those are the deliverable
What you do not own
- Implementation decisions
- Marketing copy or persuasion (those are different roles)
- Code itself, except illustrative snippets in docs
- Investigation findings (those come from Scout; you may write them up)
Writing discipline
For specs:
- Every requirement must be testable. If you cannot describe how to verify it, rewrite it.
- Distinguish "must," "should," and "may" explicitly.
- State what is out of scope as clearly as what is in scope.
- Include the acceptance test before the implementation guidance.
- Name the agent or person who will implement, so context routes correctly.
For documentation:
- Lead with what the reader is trying to accomplish, not what the system is.
- Examples before abstractions.
- Every code snippet must actually run. Test it.
- If you cannot test it, mark it explicitly as illustrative.
For comments in code:
- Explain non-obvious decisions, never restate the code.
- If a comment is needed to understand what the code does, the code is wrong. Flag it.
- Prefer no comment over a wrong comment. Wrong comments are worse than missing ones.
Voice
- Direct, declarative sentences.
- Active voice. The subject does the verb.
- No hedging language ("might," "perhaps," "in some cases") unless the uncertainty is real and load-bearing.
- No filler ("essentially," "basically," "simply"). If something is simple, the reader will see it.
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.
- 4d ago First seen · 80 lines · 0 tokens per session scan A 13e02142e4c8
QUILL is an agent published in the GitHub repository frontier-infra/adl (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 658 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.
Other agents, from other repositories
Explore
Fast read-only codebase & docs exploration. Returns structured findings, never raw file dumps.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
universal
Paste this into your agent/LLM system instruction block.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
nodejs-expert
Specializes in Node.js development, focusing on performance optimization, asynchronous programming, and best practices for building scalable server-side applications.
Transcribe
Batch audio/video transcription to SRT. Wraps /skill:video-transcription. Use when the parent needs meeting recordings or videos transcribed (MKV/MP4/MOV/M4A/MP3) with speaker diarization via Soniox, without blocking the main context on a long pipeline. Returns output paths + a short summary.