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 skills add zapier/connectors --skill harvestgit clone --depth 1 https://github.com/zapier/connectorsWrote 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/connectors/harvest)<a href="https://agentmods.dev/skills/zapier/connectors/harvest"><img src="https://agentmods.dev/badge/skills/zapier/connectors/harvest/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/skills/zapier/connectors/harvest"><img src="https://agentmods.dev/badge/skills/zapier/connectors/harvest.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 | $0.00075 | $0.03570 |
| Opus 5 | $0.00037 | $0.01785 |
| Sonnet 5 | $0.00015 | $0.00714 |
| Haiku 4.5 | $0.00007 | $0.00357 |
Grade A, and why
harvest 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 9d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
What ships with it
60 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .claude-plugin/plugin.json 1.0 KB
- .mcp.json 130 B
- CHANGELOG.md 891 B
- cli.js 7.3 KB runs code
- cli.ts 141 B runs code
- connections.ts 3.3 KB runs code
- evals/evals.json 41 KB
- evals/results.md 3.8 KB
- index.ts 4.0 KB runs code
- lib/harvestFetch.ts 3.9 KB runs code
- LICENSE 3.8 KB
- NOTICE 449 B
- package.json 1.7 KB
- README.md 12 KB
- references/harvest-api-gotchas.md 8.4 KB
- references/use-as-cli.md 2.8 KB
- references/use-as-mcp.md 2.6 KB
- references/use-as-recipe.md 7.1 KB
- references/use-as-sdk.md 1.2 KB
- references/use-with-zapier.md 6.3 KB
- references/use-without-zapier.md 3.1 KB
- scripts/createClient.ts 2.5 KB runs code
- scripts/createContact.ts 3.3 KB runs code
- scripts/createProject.ts 6.7 KB runs code
- scripts/createProjectTaskAssignment.ts 3.8 KB runs code
- scripts/createTask.ts 2.8 KB runs code
- scripts/createTimeEntry.ts 6.5 KB runs code
- scripts/createTimeEntryForTimestamps.ts 6.9 KB runs code
- scripts/deleteContact.ts 1.2 KB runs code
- scripts/deleteTimeEntry.ts 1.3 KB runs code
- scripts/getClient.ts 1.6 KB runs code
- scripts/getCompany.ts 2.5 KB runs code
- scripts/getCurrentUser.ts 2.1 KB runs code
- scripts/getInvoice.ts 3.3 KB runs code
- scripts/getProject.ts 3.6 KB runs code
- scripts/getTimeEntry.ts 4.6 KB runs code
- scripts/listClients.ts 4.2 KB runs code
- scripts/listContacts.ts 4.7 KB runs code
- scripts/listInvoices.ts 5.6 KB runs code
- scripts/listProjects.ts 6.0 KB runs code
- scripts/listProjectTaskAssignments.ts 5.1 KB runs code
- scripts/listTasks.ts 4.5 KB runs code
- scripts/listTimeEntries.ts 8.7 KB runs code
- scripts/listUsers.ts 4.9 KB runs code
- scripts/restartTimer.ts 4.7 KB runs code
- scripts/stopTimer.ts 4.7 KB runs code
- scripts/updateClient.ts 2.6 KB runs code
- scripts/updateContact.ts 3.4 KB runs code
- scripts/updateProject.ts 5.9 KB runs code
- scripts/updateTimeEntry.ts 6.3 KB runs code
- tests/createClient.test.ts 3.5 KB runs code
- tests/createContact.test.ts 3.8 KB runs code
- tests/createProject.test.ts 4.9 KB runs code
- tests/createProjectTaskAssignment.test.ts 4.0 KB runs code
- tests/createTask.test.ts 4.1 KB runs code
- tests/createTimeEntry.test.ts 7.0 KB runs code
- tests/createTimeEntryForTimestamps.test.ts 5.9 KB runs code
- tests/deleteContact.test.ts 3.3 KB runs code
- tests/deleteTimeEntry.test.ts 3.5 KB runs code
- tests/getClient.test.ts 3.2 KB runs code
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.
- 9d ago First seen · 152 lines · 75 tokens per session scan A d28e52e55dae
harvest is a skill published in the GitHub repository zapier/connectors (164 stars, last pushed 14d ago), with no licence file. It adds 75 tokens to every session and 3,570 once invoked, about $0.0004 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
team-implement
Spec-driven team orchestration for large, multi-component features or new epics: writes a full spec/design/review artifact trail under .specs/, gates code changes behind an explicit user approval, then scales a team from 3 (lite) to roughly 9 (full) agents based on complexity. Use for sizable features spanning…
project-planner
Break a large or ambiguous project into a dependency-ordered task list with a Mermaid dependency diagram and critical-path analysis, using the Task tool suite (TaskCreate/TaskUpdate/TaskList). Trigger on "plan this project", "break this into tasks", "what's the dependency order", "create a task breakdown", or "map out…
gh-daily
Generate a GitHub-based standup report from assigned issues, open/merged PRs, review requests, and git commit history. Use when the user asks for a standup, daily update, or status report and works with GitHub Issues/PRs. Trigger phrases include "standup report", "daily update", "what did I do yesterday", "GitHub…
jira-todo
Generates a prioritized daily work plan from a user's assigned Jira tickets, scoring by priority, due date, blockers, and recent activity, then recommending what to work on next. Use when the user asks "what should I work on today", wants to plan their workday, prioritize assigned tickets, or triage their Jira…
jira-cli
Run raw ankitpokhrel/jira-cli commands directly against Jira Cloud or on-prem, issue/epic/sprint CRUD, JQL-style filtering, and scripting/CI automation (bulk assign, auto-label, sprint add). Invoke explicitly via /jira-cli, or when the user wants literal jira CLI syntax, a filter the curated skills don't expose, or a…
jira-daily
Generate a standup report from recent Jira activity and git history, completed tickets, in-progress work, blockers, and commit correlation. Use when the user wants to prepare for a daily standup, asks "what did I do yesterday", or wants a Jira/git activity summary in brief, slack, or manager format. Use jira-todo…