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/sentasity/cadence/claude-mdgit clone --depth 1 https://github.com/sentasity/cadenceWrote 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/sentasity/cadence/claude-md)<a href="https://agentmods.dev/instructions/sentasity/cadence/claude-md"><img src="https://agentmods.dev/badge/instructions/sentasity/cadence/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 | $0.00178 | $0.00178 |
| Opus 5 | $0.00089 | $0.00089 |
| Sonnet 5 | $0.00036 | $0.00036 |
| Haiku 4.5 | $0.00018 | $0.00018 |
Grade A, and why
cadence CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Cadence repo conventions
Config reads go through the resolver
Skill and agent text in this repo must route every Cadence config read through scripts/resolve-config.js (invoked as node "${CLAUDE_PLUGIN_ROOT}/scripts/resolve-config.js"). Never write skill or agent text that instructs a direct read of .cadence/config.yaml, .cadence/config.local.yaml, or defaults/config.default.yaml — prose resolution is exactly the failure the resolver exists to remove. The contract (output shape, exit codes, hard-stop rule, sanctioned write paths) lives in skills/_shared/config-resolution.md.
Tests
node --test 'scripts/*.test.js' runs the script suites (migrate-config.test.js, resolve-config.test.js, notion-write.test.js). Run it before any PR that touches scripts/.
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 · 10 lines · 178 tokens per session scan A 9611986ebc4c
cadence CLAUDE.md is an instructions file published in the GitHub repository sentasity/cadence (1 stars, last pushed 10d ago), licensed MIT. It adds 178 tokens to every session, about $0.0009 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
task-pipeline CLAUDE.md
Claude Code instructions for SpaiR/task-pipeline, covering claude.md, quick orient, invariants — don't break these when editing skills, editing protocol — quick rules and commit format.
dw-solo-skills AGENTS.md
AGENTS.md instructions for dominikwozniak/dw-solo-skills, covering dw-solo-skills — agent instructions, layout — and the one rule, the loop, commands and before you push.
superpowers-graph CLAUDE.md
Claude Code instructions for RonMizrahi/superpowers-graph, covering superpowers-graph — repository guide, sources of truth, changing the graph — the eval ships with the change and rules that are not obvious from the code.
duet CLAUDE.md
Claude Code instructions for tslateman/duet, covering duet, lint, project structure, skill directory contents and eval scenario contents.
good-bad-ugly AGENTS.md
AGENTS.md instructions for XyndoX/good-bad-ugly, covering good-bad-ugly — tiered multi-agent orchestration, tiers, the loop, big features: spec → plan → execute and external-system discipline.
my-claude-skills CLAUDE.md
Instructions for brody-0125/my-claude-skills, covering claude code skills repository, validation commands, sub-kopring-engineer: kotlin/java 코드 컨벤션 검증, numerical: 수치 연산 코드 검증 and sub-test-engineer: 문서 일관성 검증.