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/zapier/agent-skills/modifynpx skills add zapier/agent-skills --skill modifygit clone --depth 1 https://github.com/zapier/agent-skillsWrote 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/zapier/agent-skills/modify)<a href="https://agentmods.dev/skills/zapier/agent-skills/modify"><img src="https://agentmods.dev/badge/skills/zapier/agent-skills/modify.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 | $0.00054 | $0.05144 |
| Opus 5 | $0.00027 | $0.02572 |
| Sonnet 5 | $0.00011 | $0.01029 |
| Haiku 4.5 | $0.00005 | $0.00514 |
Grade A, and why
workflows-modify 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.
How it starts
The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Zapier Workflows Modify
Modifying a deployed workflow follows a discovery, fetch, edit, publish, verify pattern. There are two ways to publish a change, and the user chooses between them:
- Direct publish — one
publish-workflow-versioncall that creates and activates a new version immediately. Fastest path when the user wants the change live now. - Through a draft — save the change into the workflow's server draft (the working copy shared with the Zapier editor), then either publish the draft or leave it open for the user to review and publish later.
Publishing writes to the user's Zapier account, so get explicit confirmation before publishing either way.
Use the public SDK CLI experimental command surface. Do not use zapier-sdk-code-substrate.
Compatibility Gate
Before using this skill, run the workflows-doctor bundle compatibility check. If workflows-doctor is not installed or cannot be loaded, run workflows-install or install workflows-doctor from zapier/agent-skills before continuing. If workflows-doctor reports SDK/skill drift, follow its refresh instructions, stop this skill invocation, reload the agent workspace if needed, and ask the user to rerun the original request.
Step 1: Identify The Workflow
If the user provides a workflow ID, use it directly. Otherwise list workflows and find the matching one by name or description:
zapier-sdk --experimental list-workflows --json
If multiple workflows match, show candidates and ask the user which one to modify.
Step 2: Check For Open Drafts And Pick The Path
zapier-sdk --experimental list-workflow-drafts <workflow-id> --json
The list returns open drafts, most recently edited first. An open draft always holds unpublished work (publishing consumes drafts, so a leftover one was never published).
- An open draft exists: work through the draft. It holds the user's in-progress edits and your change applies on top of it — and a direct publish would be rejected by the server's open-draft guard anyway (see Step 6A). If several are open, tell the user and confirm which to use.
- No open draft: both paths are available. If the user's request already implies immediate publish ("fix it and ship it"), direct publish is the shorter path. If they want to review first, work incrementally, or hand off to the editor, use a draft. When the intent is unclear, ask: publish directly once the change is ready, or stage it as a draft to review/publish later?
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 · 297 lines · 54 tokens per session scan A b1473745ab6a
workflows-modify is a skill published in the GitHub repository zapier/agent-skills (17 stars, last pushed 11d ago), licensed MIT. It adds 54 tokens to every session and 5,144 once invoked, about $0.0003 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 skills, from other repositories
trace-and-isolate
Applies systematic tracing and isolation techniques to pinpoint exactly where a bug originates in code. Use when a bug is hard to locate, code is not working as expected, an error or crash appears with unclear cause, a regression was introduced between recent commits, or you need to narrow down which component…
testing-anti-patterns
Reviews test code to identify and fix common testing anti-patterns including flaky tests, over-mocking, brittle assertions, test interdependency, and hidden test logic. Flags bad patterns, explains the specific defect, and provides corrected implementations. Use when reviewing test code, debugging intermittent or…
handoff-protocols
Manages work transitions between team members or agents by creating structured handoff documents, summarizing project status, documenting key decisions, blockers, and open questions, and generating onboarding briefs. Use when someone needs to hand off, hand over, or transition a project; pass work to another person or…
parallel-investigation
Coordinates parallel investigation threads to simultaneously explore multiple hypotheses or root causes across different system areas. Use when debugging production incidents, slow API performance, multi-system integration failures, or complex bugs where the root cause is unclear and multiple plausible theories exist…
hypothesis-testing
Applies the scientific method to debugging by helping users form specific, testable hypotheses, design targeted experiments, and systematically confirm or reject theories to find root causes. Use when a user says their code isn't working, they're getting an error, something broke, they want to troubleshoot a bug, or…
root-cause-analysis
Performs systematic root cause analysis to identify the true source of bugs, errors, and unexpected behavior through structured investigation phases — not just treating symptoms. Use when a user reports a bug, crash, error, or broken behavior and needs to debug, troubleshoot, or investigate why something is not…