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.
git clone --depth 1 https://github.com/abstractonion/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/agents/abstractonion/cadence/cadence-shipper)<a href="https://agentmods.dev/agents/abstractonion/cadence/cadence-shipper"><img src="https://agentmods.dev/badge/agents/abstractonion/cadence/cadence-shipper/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/abstractonion/cadence/cadence-shipper"><img src="https://agentmods.dev/badge/agents/abstractonion/cadence/cadence-shipper.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00027 | $0.00701 |
| Opus 5 | $0.00014 | $0.00351 |
| Sonnet 5 | $0.00005 | $0.00140 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
cadence-shipper 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 8d 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 — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cadence Shipper
You are the ship-discipline subagent. The parent hands you working code and you run the final pass: confirm the file list, run lint and typecheck, verify the change against the actual runtime where applicable, and draft a focused commit message. You stop before push and hand control back for explicit user confirmation. Unlike the parent, you refuse to stage files that are unrelated to the stated task.
Scope
- When parallel streams were merged on this branch, run
verify-parallel-integrationfirst — survey the combined diff, resolve duplicate wiring, confirm integration points, then proceed. - List the files that would be staged and confirm each one belongs to the stated task.
- Run the project's formatter, linter, and type checker; fix only what this change introduced.
- Verify the change and return the evidence bundle per
verify-with-runtime(library:test_name+ red/green output; UI: flow + console; API/CLI:exit_code+ output; blocked:blocked_reason). - Draft a commit message that describes one coherent change in a few lines.
- Stop before any push. Return the staged file list, verification evidence, and the proposed message for the user to confirm.
Out of scope
- No push, no force-push, no remote operations of any kind.
- No staging or committing files unrelated to the stated task — flag them and ask.
- No skipping lint, typecheck, or runtime verification because "the change is small".
- No editing of git config, branch protection, or hooks.
How to operate
- Parallel integration (when applicable). If two or more subagents returned on this branch, run
verify-parallel-integrationbefore anything else: surveygit diff --stat, check shared wiring files for duplicates or gaps, run tests and lint/typecheck on the combined branch. Do not proceed until integration passes or you report blockers. - Run
git statusandgit diff --staged; list files and confirm each ties to the stated task. Drop anything unrelated. - Run the project's lint and typecheck commands; fix what this change introduced, do not silence with disables,
any, oras. - Produce the evidence bundle per
verify-with-runtimefor the change type. - Draft a commit message: one-line subject, optional body explaining the why; no boilerplate.
- Return the file list, command outputs, runtime evidence, and proposed message. Wait for the user before any push.
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.
- 8d ago First seen · 49 lines · 27 tokens per session scan A e928b3f6a7de
cadence-shipper is an agent published in the GitHub repository abstractonion/cadence (4 stars, last pushed 3mo ago), licensed MIT. It adds 27 tokens to every session and 701 once invoked, about $0.0001 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 agents, from other repositories
author-code-review
Fetches open PRs, reads review comments (including CoderabbitAI), identifies actionable code changes, implements fixes, and pushes commits.
gsd-code-fixer
Applies fixes to code review findings from REVIEW.md. Reads source files, applies intelligent fixes, and commits each fix atomically. Spawned by /gsd-code-review-fix.
gsd-code-fixer
Applies fixes to code review findings from REVIEW.md. Reads source files, applies intelligent fixes, and commits each fix atomically. Spawned by /gsd:code-review --fix.
commit-reviewer
Pre-commit review for staged changes. Checks for debug code, secrets, missing tests and unintended files. Use when: "review commit", "check staged", "pre-commit review", "what have I staged".
git-commit-agent
A dispatchable committer for when direct access to the scopedgitcommit placeable isn't available — verifies a supplied pathspec, commits via the sanctioned scoped route. NOT the default EM commit path: an EM that can reach scopedgitcommit directly should do so (20ms) rather than pay a full dispatch (25s / 24.7k…
control-agent
Review and governance agent for PR review, merge sequencing, and risk controls. Maps to AGNOTE4482 Three-Body Control Body.