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/a2uicatalog/a2ui/claude-mdgit clone --depth 1 https://github.com/a2uicatalog/a2uiWrote 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/a2uicatalog/a2ui/claude-md)<a href="https://agentmods.dev/instructions/a2uicatalog/a2ui/claude-md"><img src="https://agentmods.dev/badge/instructions/a2uicatalog/a2ui/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 | $0.01588 | $0.01588 |
| Opus 5 | $0.00794 | $0.00794 |
| Sonnet 5 | $0.00318 | $0.00318 |
| Haiku 4.5 | $0.00159 | $0.00159 |
Grade A, and why
a2ui 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
a2ui-catalogue — Working Rules
Declarative-first repo. State, policy, and processes are declared in
project.yaml; ops/ops.py executes them. Read project.yaml before
operating — it is the inventory (deployments, script IDs, properties,
staging policy, declared debt). Never carry identifiers in conversation
memory when the manifest declares them.
Operations discipline
- Every operation goes through a declared process:
python3 ops/ops.py list→python3 ops/ops.py run <process>. If the operation you need isn't declared, DECLARE IT inproject.yamlprocesses:first, then run it. Improvised command sequences (rawclasp push/clasp deploy, ad-hoc regeneration chains) are the failure mode this system exists to prevent. - After editing
atoms/schema.yaml→ops.py run atom-change. - After editing
spec/or prompt contracts →ops.py run prompt-update(it bakes in the gemini_handoff cache bump — do not skip it). - Renderer code changes →
ops.py run renderer-release(deploys in place to the public deployment from the manifest inventory). - Commits:
python3 ops/ops.py commit "<message>"— stamps per the sync-window time mapping (09:00-11:59→08:00, 14:00-17:59→13:30, otherwise 13:00, Europe/Paris). Push:ops.py run repo-publish. - Every run logs to
ops/log.jsonl(local tier) — check it before re-diagnosing something a previous run already recorded.
Publication boundaries (hard rules)
- Nothing new is published to a2uicatalog.ai or any public surface
without explicit per-artifact opt-in from Curtis. Publication is
declared in
project.yaml(policy.published,published_prompts) and enforced bytests/test_project_manifest.py. - Atoms carry
stage: preview | stable(stable = default). Preview atoms are repo-only; all publication pipelines filter on the field (tests/test_staging.pyenforces). Promotion = delete the stage lineops.py run atom-change. New dev-first atoms START as preview.
- Private tier (
ops/,**/Code.private.gs,.clasp.json) must never be tracked — the manifest audit fails the build if it is. - Secrets live in Script Properties only (key names declared in
project.yaml); never in code, payloads, or tracked files.
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 · 116 lines · 1,588 tokens per session scan A 8cec04524e38
a2ui CLAUDE.md is an instructions file published in the GitHub repository a2uicatalog/a2ui (4 stars, last pushed 5d ago), licensed MIT. It adds 1,588 tokens to every session, about $0.0079 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.
Other instructions, from other repositories
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
InvestSkill GEMINI.md
Gemini CLI instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
she-love-me CLAUDE.md
Instructions for 863401402/she-love-me, covering claude.md and 唯一工作流.
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
slivingdoc AGENTS.md
AGENTS.md instructions for baalimago/slivingdoc, covering agents.md — slivingdoc, architecture, package map, event flow and startup wiring (main.go).
deckforge AGENTS.md
Instructions for tph-kds/deckforge, covering deckforge agent entry point, code intelligence, read order, default routing and non-negotiable implementation rules.