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/sjhorn/single_child_two_dimensional_scroll_view/claude-mdgit clone --depth 1 https://github.com/sjhorn/single_child_two_dimensional_scroll_viewWrote 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/sjhorn/single_child_two_dimensional_scroll_view/claude-md)<a href="https://agentmods.dev/instructions/sjhorn/single_child_two_dimensional_scroll_view/claude-md"><img src="https://agentmods.dev/badge/instructions/sjhorn/single_child_two_dimensional_scroll_view/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 5.1 | $0.00834 | $0.00834 |
| Opus 5 | $0.00417 | $0.00417 |
| Sonnet 5 | $0.00167 | $0.00167 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
single_child_two_dimensional_scroll_view 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 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.
How it starts
The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Rules
- All work starts from a GitHub issue. No issue → create one before writing code.
- TDD is mandatory. Failing test → implement → refactor → commit.
qaagent gates every commit. Never runflutter test,flutter analyze,dart formatdirectly — alwaysscripts/ci/wrappers.- Every public symbol has
///dartdoc. Zerodart docwarnings. - 90% test coverage for all code
- Commit format:
type(scope): description— one ROADMAP checkbox per commit max. - No raw shell in Bash tool calls. In Bash tool calls, never use
$(),sed,|,>,&&,||,tr,2>&1. Never prefix commands withbash— run scripts directly (e.g.scripts/ci/ci_gate.sh, notbash scripts/ci/ci_gate.sh). Thescripts/ci/wrappers handle shell complexity internally. For ad-hoc commands, usescripts/ci/capture.sh <label> <command> [args...]. - After any user correction → update
tasks/lessons.md. - Domain layer (
lib/src/domain/) is pure Dart — no Flutter imports. - No
dynamictypes. - No business logic in widgets.
Reference ROADMAP.md and tasks/lessons.md for memory
Agents
Delegate: "use the <name> agent to <task>"
| Task | Agent |
|---|---|
| Entities, value objects, business logic | domain |
| Platform services, data sources, integrations | infrastructure |
| Widgets, render objects, UI components | presentation |
| End-to-end / integration tests | integration |
| Performance benchmarks | benchmark |
| Docs, examples, README, CHANGELOG | docs |
| Run tests, analyze, format, coverage | qa |
| GitHub issues, PRs, labels, branches | github |
| Publish to pub.dev | publish |
Before every commit → qa. After public API changes → docs.
Cross-layer order: domain → infrastructure → presentation → qa → docs → commit
Workflow
- Issue —
use the github agent to start <number>(orcreateif none exists) - Red —
use the <owning> agent to write a failing test for <task>→use the qa agent to confirm it fails - Green —
use the <owning> agent to implement minimum to pass→use the qa agent to confirm it passes - Refactor —
use the <owning> agent to refactor→use the qa agent to confirm still green - Gate —
use the qa agent to run the full gate - Commit —
type(scope): description - Repeat steps 2–6 for each behaviour in the issue
- PR —
use the github agent to pr <number>→ tick ROADMAP checkbox - Stop — Do not start the next issue until the PR is submitted
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 · 64 lines · 834 tokens per session scan A b99330be3794
single_child_two_dimensional_scroll_view CLAUDE.md is an instructions file published in the GitHub repository sjhorn/single_child_two_dimensional_scroll_view (5 stars, last pushed 5mo ago), licensed BSD-3-Clause. It adds 834 tokens to every session, about $0.0042 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 2026-09-04.
Other instructions, from other repositories
wallfacer AGENTS.md
AGENTS.md instructions for changkun/wallfacer: If you didn't add a test, you didn't fix a bug. Every bug fix must include a reproducible test that fails without the fix and passes with it. You commit frequently, one small scope diff at a time. Push to main once a full batch of work is complete and verified. Leftover…
aristo CLAUDE.md
Instructions for aretta-ai/aristo, covering claude.md — aristo working agreement, §1. commit size — small or medium only, §2. commit messages — semantic / conventional, §3. changelog.md — one line per commit, in the same commit and §4. test-first — no test, no claim of correctness.
planning-with-files AGENTS.md
AGENTS.md instructions for OthmanAdi/planning-with-files, covering agents.md — planning-with-files agent reference card, commit rules, release checklist (12 steps), version bump scope and changelog format.
dario CLAUDE.md
Claude Code instructions for askalf/dario, covering dario — notes for claude code (and other llm coding agents), commits and prs, style, scope and codex drift runner.
spec-driven-tdd AGENTS.md
Instructions for strelov1/spec-driven-tdd: This repo is a skill-pack. When implementing an OpenSpec change, invoke the spec-driven-tdd skill and follow its lifecycle: plan in OpenSpec, isolate in a worktree, implement each task via TDD → simplify → review, then finish + archive.
bro-skills copilot-instructions.md
Copilot instructions for wedabro/bro-skills, covering copilot instructions for bro-skills, 1. supreme order, 2. bro-skills protocol, 3. language & code and 4. safety.