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 instructions/jermolene/twillm/claude-mdgit clone --depth 1 https://github.com/Jermolene/twillmWrote 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/instructions/jermolene/twillm/claude-md)<a href="https://agentmods.dev/instructions/jermolene/twillm/claude-md"><img src="https://agentmods.dev/badge/instructions/jermolene/twillm/claude-md.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 | $0.01206 | $0.01206 |
| Opus 5 | $0.00603 | $0.00603 |
| Sonnet 5 | $0.00241 | $0.00241 |
| Haiku 4.5 | $0.00121 | $0.00121 |
Grade A, and why
twillm CLAUDE.md 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 5d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working on twillm
This is the twillm project repo, not an end-user vault. twillm is a Node CLI that materialises a TiddlyWiki working directory (twillm-wiki/) in a user's repo and serves their Markdown vault as a live-watched TiddlyWiki.
End-user docs are in README.md. Architecture notes, design decisions, and the TODO list are in DEVELOPMENT.md. Read both before non-trivial changes.
Repo layout
cli.js— CLI entry point. Detects the user's vault, materialisestwillm-wiki/, spawns TiddlyWiki.template-wiki/— the wiki template that gets copied into a user'stwillm-wiki/on first run. Edit here to change what users get.vault/— test fixture. Sample Markdown content used bynpm startandnpm run build.handoff.md,README.md,CLAUDE.md— docs.twillm-wiki/— generated at runtime bynpm start/npm run build. Gitignored. Don't commit.
Editing the test vault
The tiddlers in vault/ are demo content. Add to them when you want to exercise something live (rendering, watcher behaviour, link resolution). Same conventions a user would follow:
- Markdown with YAML frontmatter
- One tiddler per file:
vault/<Title>.md - Frontmatter
titleshould match filename tagsas YAML arrays:tags: [concept, multi word tag]- Don't include
type—.mdimpliestext/x-markdownand it round-trips out created/modifiedare optional; if present they round-trip as ISO-8601 strings- Wiki links:
[[Target Title]]or[[Display|Target Title]]
Editing template-wiki/
This is what users get. Be conservative — new files ship to everyone who runs npx github:Jermolene/twillm. Changes to existing files only reach fresh materialisations: files already present in a user's twillm-wiki/ are never overwritten.
template-wiki/tiddlywiki.info— wiki configuration. Plugins listed here are required of every user.template-wiki/tiddlers/$__SiteTitle.tid,$__SiteSubtitle.tid— defaults users will probably overridetemplate-wiki/tiddlers/$__config_SyncPollingInterval.tid— controls how often the browser polls. 2 seconds today.template-wiki/tiddlers/vault-loader/tiddlywiki.files— overwritten at runtime by cli.js with the user's absolute vault path. Don't rely on its contents.
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.
- 5d ago First seen · 70 lines · 1,206 tokens per session scan A 8d092f88bcaf
twillm CLAUDE.md is an instructions file published in the GitHub repository Jermolene/twillm (22 stars, last pushed 1mo ago), licensed BSD-3-Clause. It adds 1,206 tokens to every session, about $0.0060 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.