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 commands/avinava/document-design-system/referencegit clone --depth 1 https://github.com/Avinava/document-design-systemWhat 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 | $0.00032 | $0.00133 |
| Opus 5 | $0.00016 | $0.00067 |
| Sonnet 5 | $0.00006 | $0.00027 |
| Haiku 4.5 | $0.00003 | $0.00013 |
Grade A, and why
reference 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.
This is a copy
84% identical to adr — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Use the writing-documents skill.
Type slug: reference
Load references/type-reference.md, references/writing.md, references/evidence.md.
Default output is Markdown in the user's project at this type's conventional path.
Do not assemble HTML, pick a theme, inline CSS, or run build_document.py unless
the user asked for HTML, PDF, print, or designed output.
If they did, also load references/output.md and core/.
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.
- yesterday First seen · 12 lines · 32 tokens per session scan A 1b4cde3eb1c4
reference is a command published in the GitHub repository Avinava/document-design-system (2 stars, last pushed 6d ago), licensed MIT. It adds 32 tokens to every session and 133 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 84% identical to adr, differing in 6 lines, and is treated as a copy.
Other commands, from other repositories
fork-pov
Fork pov.md for installer taste, or append a one-liner to gotchas.md after a real agent failure.
axstream-teach
Compile a UI task into a fast replayable macro (do it once, instant forever).
axstream
Status of fast computer use — macro library, verified state, prerequisites.
teach
Explain a CANON rule or decision in plain language with before/after examples.
review-renovate
Review and merge renovate PRs with automerge configuration updates.
monitor-ci
Monitors pull request CI checks until they are resolved (pass or fail).