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/krodak/clickup-cli/releasing-clickup-clinpx skills add krodak/clickup-cli --skill releasing-clickup-cligit clone --depth 1 https://github.com/krodak/clickup-cliWrote 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/krodak/clickup-cli/releasing-clickup-cli)<a href="https://agentmods.dev/skills/krodak/clickup-cli/releasing-clickup-cli"><img src="https://agentmods.dev/badge/skills/krodak/clickup-cli/releasing-clickup-cli.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 | $0.00050 | $0.00981 |
| Opus 5 | $0.00025 | $0.00491 |
| Sonnet 5 | $0.00010 | $0.00196 |
| Haiku 4.5 | $0.00005 | $0.00098 |
Grade A, and why
releasing-clickup-cli scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
SHA=$(curl -sL https://registry.npmjs.org/@krodak/clickup-cli/-/clickup-cli-<version>.tgz | shasum -a 256 | cut -d' ' -f1) How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Versioning
| Change type | Bump |
|---|---|
| Bug fix | patch (x.y.Z) |
| New feature, backward compatible | minor (x.Y.0) |
| Breaking change | major (X.0.0) |
Pre-release checklist
-
npm run typecheckpasses -
npm run lintpasses -
npm testpasses (includes version sync test) -
npm run buildsucceeds - New commands added to
src/commands/metadata.ts(completion test will fail otherwise)
Release steps
1. Commit feature/fix changes first
Do NOT mix feature commits with version bump commits.
2. Bump version
npm version <version> --no-git-tag-version
3. Sync all version-tracked files
node --import tsx scripts/sync-command-docs.ts
This updates:
docs/commands.mdquick reference tableskills/clickup-cli/SKILL.mdversion header (line 6)skills/clickup-cli/SKILL.mdversion check hint (line 10).claude-plugin/plugin.jsonversion field
The version synchronization test in tests/unit/ verifies these stay in sync.
4. Commit and tag
git add package.json package-lock.json .claude-plugin/plugin.json docs/commands.md skills/clickup-cli/SKILL.md
git commit -m "bump v<version>"
git tag v<version>
git push origin main --tags
5. Wait for CI
gh run watch --repo krodak/clickup-cli --exit-status $(gh run list --repo krodak/clickup-cli --workflow release.yml --limit 1 --json databaseId -q '.[0].databaseId')
The release workflow runs: typecheck, test, build, npm publish (OIDC), GitHub Release creation.
6. If CI fails
Common failures:
npm cifails: peer dep conflict (typescript-eslint vs TypeScript 6)..npmrchaslegacy-peer-deps=true.- Completion test fails:
metadata.tsis missing a new command or flag. Add it, amend, re-tag, force push. - npm publish fails "already published": Version already exists on npm from a previous attempt. Bump to next version.
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.
- 4d ago First seen · 129 lines · 50 tokens per session scan A 1020ba42858e
releasing-clickup-cli is a skill published in the GitHub repository krodak/clickup-cli (115 stars, last pushed yesterday), licensed MIT. It adds 50 tokens to every session and 981 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
clickup-cli
ClickUp CLI for managing tasks, sprints, comments, statuses, Docs, and archiving. Use when the user needs to interact with ClickUp — creating/editing/archiving tasks, checking sprint status, adding comments, linking PRs, managing Docs and pages, or searching tasks. Includes a generic clickup api passthrough covering…
pickle-slack
Pickle for Slack — scans every Slack channel, DM, and group DM you're in for a given time window. Extracts messages where YOUR action is needed AND tracks work you delegated to others that needs follow-up. Creates entries in a dedicated Slack List (or Canvas fallback) + sets Slack reminders — all kept SEPARATE from…
ClickUp Automation
Automate ClickUp workspace management, task workflows, time tracking, and team productivity.
pickle-clickup
Pickle for ClickUp — scans every ClickUp channel, DM, and group DM you follow for a given time window. Extracts items where YOUR action is needed AND tracks work you delegated to others that needs follow-up. Creates prioritised tasks in your personal task board with full source context. Usage: /pickle-clickup [time]…
pickle-teams
Pickle for Microsoft Teams — scans all your Teams channels, chats (1:1, group, meetings), and DMs for a given time window. Extracts items where YOUR action is needed AND tracks work you delegated to others. Creates tasks in Microsoft To Do. Usage: /pickle-teams [time] [followup] — e.g. /pickle-teams 24h |…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.