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/jackhutson/todoist-plugin/setupnpx skills add jackhutson/todoist-plugin --skill setupgit clone --depth 1 https://github.com/jackhutson/todoist-pluginWhat 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 | $0.00084 | $0.00599 |
| Opus 5 | $0.00042 | $0.00300 |
| Sonnet 5 | $0.00017 | $0.00120 |
| Haiku 4.5 | $0.00008 | $0.00060 |
Grade B, and why
setup scanned grade B 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
(`.claude/settings.json`) or user (`~/.claude/settings.json`) — or skip. What it actually says
Todoist Setup
Bootstrap the td CLI transport. No methodology, no questionnaire.
Steps
1. Installation
command -v td || echo missing. If missing, guide:
npm install -g @doist/todoist-cli (requires Node 20+), then re-check.
2. Version floor
td --version must be ≥ 1.75.0. If older: td update (or
npm update -g @doist/todoist-cli).
3. Authenticate
td auth status. If unauthenticated, have the user run td auth login
(browser OAuth; token lands in the OS keyring). Headless machines:
td auth login --no-browser-open. Never run td auth token view.
4. Health check
td doctor. Report problems verbatim; the common fix is re-login.
5. Permission ergonomics (offer, don't impose)
Offer to add read-only td commands to the Claude Code permission
allowlist so daily use doesn't prompt. Ask which scope — project
(.claude/settings.json) or user (~/.claude/settings.json) — or skip.
Merge these into permissions.allow (create the file if absent,
preserve existing entries):
Bash(td today*), Bash(td inbox*), Bash(td upcoming*),
Bash(td task list*), Bash(td task view*), Bash(td completed list*),
Bash(td project list*), Bash(td section list*), Bash(td label list*),
Bash(td filter list*), Bash(td auth status*), Bash(td doctor*)
Mutations stay unlisted (they prompt normally); destructive commands always prompt.
6. Verify & seed
td today runs clean → seed the structure cache: run td project list
and td label list, write the names to
~/.config/todoist-plugin/structure.md (shape defined in the todoist
skill), then report ready and mention /todoist:capture,
/todoist:daily, /todoist:triage.
Migrating from v1 (MCP)
v1 of this plugin used the Doist MCP server. Once setup succeeds the MCP
connection is unused — remove any todoist entry via /mcp. Details in
CHANGELOG 2.0.0.
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.
- 2d ago First seen · 61 lines · 84 tokens per session scan B aa6039e1a14c
setup is a skill published in the GitHub repository jackhutson/todoist-plugin (2 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 599 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
use-agent-browser-for-airi
Test AIRI display-model imports with agent-browser across stage-tamagotchi Electron, stage-web, and stage-pocket mobile web layouts. Use when uploading and verifying contributor-supplied Live2D ZIP, VRM, or MMD ZIP/PMX/PMD files through AIRI's model selector, including onboarding bypass, format-specific import…
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
browser_cdp
通过 Chrome DevTools Protocol (CDP) 连接已运行的浏览器，或扫描本机 CDP 端口，用于远程调试与多工具共享浏览器实例。.