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 skills/crenshawdev/cadence/cad-pausenpx skills add crenshawdev/cadence --skill cad-pausegit clone --depth 1 https://github.com/crenshawdev/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/skills/crenshawdev/cadence/cad-pause)<a href="https://agentmods.dev/skills/crenshawdev/cadence/cad-pause"><img src="https://agentmods.dev/badge/skills/crenshawdev/cadence/cad-pause.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 | $0.00036 | $0.00540 |
| Opus 5 | $0.00018 | $0.00270 |
| Sonnet 5 | $0.00007 | $0.00108 |
| Haiku 4.5 | $0.00004 | $0.00054 |
Grade A, and why
cad-pause scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
<execution_context> @${CLAUDE_PLUGIN_ROOT}/cadence-core/references/git-guard.md </execution_context>
-
Set the cursor through the seam (never hand-edit STATE.md):
node "${CLAUDE_PLUGIN_ROOT}/cadence-core/bin/planning.mjs" cursor set \ --phase <current> --status paused --next-file <path>The resume pointer is a one-line "where I was" naming the next concrete action (from
$ARGUMENTS, or ask via the ask-user seam if not given) - the user's own sentence, so write it to a scratch file and pass the PATH (caller-derived text - references/conventions.md). This line IS the pause note /cad-progress surfaces.--phase <current>is required - the seam does NOT preserve a priorPhase:(it failsbad-argswithout it); supply the current phase fromcursor get, which goes in one message with step 1's protected-branch git probes - they are independent, and only a call that consumes a prior call's output is serialized. The seam derives name/total from ROADMAP and stampsUpdated:itself. Commit the cursor (docs:), or fold it into the WIP commit if one was made. Never leave the tree dirty. -
Report. One line: paused at , resume with /cad-progress.
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 · 52 lines · 36 tokens per session scan A 7e793aca1abf
cad-pause is a skill published in the GitHub repository crenshawdev/cadence (4 stars, last pushed 3d ago), licensed MIT. It adds 36 tokens to every session and 540 once invoked, about $0.0002 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 skills, from other repositories
commit
Commit the current change set with optional drift backfill (sprint mode) or as a generic Conventional Commits commit (standalone mode). Auto-detects which mode based on sprint context. Sprint mode verifies declared spec deltas (PLAN.md / SPEC.md ## Spec deltas) against the actual diff before staging; missing or…
commit-message-generator
Automatically generate conventional commit messages when user has staged changes and mentions committing. Analyzes git diff and status to create properly formatted commit messages following conventional commits specification, and appends the Assisted-by git trailer recording which AI model (Claude, GPT, Gemini, or any…
turnstile-core
Turnstile's non-negotiable rules -- gate order, TDD, brain-first, commit and reply conventions. Auto-loads whenever any turnstile skill is active.
writing-commit-messages
Use when drafting any commit message — sets format (imperative subject under 72 chars, explanatory body when the why isn't obvious from the diff) and prevents the "Fix X" one-liner reflex for non-trivial fixes.
checkpoint-commit
每完成一个 plan 步骤自动 git commit，记录到 .ddt/checkpoints.log；支持 git revert 回滚到任意 checkpoint。auto-loaded by build-api / build-web / fix 等 IMPLEMENT phase。DDT 步骤级 git commit 范式。.
gating-commits
Use when about to commit, merge, or push — runs verification (tests, typecheck, lint), confirms focus, and checks sibling hygiene (docs, tests, docstrings) BEFORE the commit lands, so "user said commit" doesn't bypass quality.