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/csthink/dashmotion/claude-mdgit clone --depth 1 https://github.com/csthink/dashmotionWhat 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 | $0.00752 | $0.00752 |
| Opus 5 | $0.00376 | $0.00376 |
| Sonnet 5 | $0.00150 | $0.00150 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
dashmotion 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 3d 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 — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — dashmotion
Operational notes for AI agents (and humans) editing this repo. What dashmotion does and how the generation works live in the README and docs/how-it-works.md — this file does not repeat them.
Mars's cross-project working philosophy (verification discipline, authorization
boundaries, how to sink learnings) lives in the global ~/.claude/CLAUDE.md and is
not duplicated here. Instructions there and in chat override this file. This file is
a prose layer — it points at the real mechanisms; it does not enforce anything. When
a convention changes, change the mechanism first, then the pointer here.
Mechanisms — follow the mechanism, don't paraphrase its details
- Release gate. Before tagging any version, both must hold:
test/run_checks.pygreen over the b1–b4 + m1–m7 fixtures (structure + per-case asserts + Mermaid fidelity), and a fresh medium-effort bianque-class diagram (30+ nodes) generating ≤ 8 min end-to-end.test/is gitignored — runner and fixtures are local-only. - Verification authority. A generated diagram is judged by the skill's bundled
skills/dashmotion/scripts/check_diagram.py(structure: overlaps, connectors through boxes, broken loops, out-of-viewBox) andcheck_fidelity.py(Mermaid labels, verbatim) — this is SKILL.md Step 6. Never verify by eyeballing or a browser screenshot: label paraphrase is invisible to the eye and silently shipped reworded labels beforecheck_fidelity.pywas mechanized.eval/holds the committed eval harness. - Timing. Always benchmark at medium / default effort, never xhigh — the effort setting alone moves latency ~3.4× and will corrupt any perf conclusion. ≤8 min is an absolute, model-agnostic UX target.
Repo conventions — non-obvious, has bitten
- What ships ≠ the repo.
npx skills addand the release zip ship onlyskills/dashmotion/. README, CHANGELOG,docs/,eval/stay in the repo and never reach an installed user — so doc-only changes need no release. - Gitignored by design:
research/(decision maps — write strategy/decision docs here, not committed) andtest/(fixtures + runner). Don't try to commit them. - Two remotes:
origin= GitHub (csthink/dashmotion),gitee= Gitee. Tags, releases and the zip go to both. Don't merge tomainor tag a release without Mars's explicit go-ahead. - Versioning rubric is in the CHANGELOG header: the dividing line is the user-facing capability surface (new input / output mode / refinement = minor) vs. generator internals (perf, workflow, layout, fixes = patch).
- Distribution & updates: users install/upgrade via
npx skills(-gfor global) or the release zip; no client auto-notifies updates. Decision detail in the gitignoredresearch/distribution-and-updates.md.
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.
- 3d ago First seen · 48 lines · 752 tokens per session scan A 1a52796fd2ec
dashmotion CLAUDE.md is an instructions file published in the GitHub repository csthink/dashmotion (159 stars, last pushed 2mo ago), licensed MIT. It adds 752 tokens to every session, about $0.0038 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
codemap AGENTS.md
Instructions for beadnall/codemap, covering codemap, if you are claude, if you are grok build, if you are another agent and the short version.
codemap copilot-instructions.md
Instructions for beadnall/codemap: This repository holds a skill for turning a codebase into an explorable isometric diagram. The full instructions are in SKILL.md — read that file and follow it when asked to map, diagram or visually explain how a system fits together.
archeyes CLAUDE.md
Instructions for thisAAY/archeyes, covering archeyes — project guide, layout, design system, commands and publishing a release.
access-to CLAUDE.md
Claude Code instructions for dougdevitre/access-to, covering claude.md — instructions for claude code, project overview, repository structure, commands and validate config files.
access-to copilot-instructions.md
Copilot instructions for dougdevitre/access-to, covering copilot instructions for access to, architecture, key conventions, file structure and code style.
master-instructional-design GEMINI.md
Gemini CLI instructions for narosemena/master-instructional-design, covering master-instructional-design — claude code context, repo structure, key constraints, development workflow and make changes to skill.md or any reference file.