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 dtormoen/tsk-tsk --skill tsk-addgit clone --depth 1 https://github.com/dtormoen/tsk-tskWrote 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/dtormoen/tsk-tsk/tsk-add)<a href="https://agentmods.dev/skills/dtormoen/tsk-tsk/tsk-add"><img src="https://agentmods.dev/badge/skills/dtormoen/tsk-tsk/tsk-add/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/dtormoen/tsk-tsk/tsk-add"><img src="https://agentmods.dev/badge/skills/dtormoen/tsk-tsk/tsk-add.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00016 | $0.00964 |
| Opus 5.5 | $0.00006 | $0.00386 |
| Sonnet 5.5 | $0.00003 | $0.00193 |
| Haiku 4.5 | $0.00002 | $0.00096 |
Grade A, and why
tsk-add 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 1mo 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Queue Task from Conversation
You are helping the user queue a task based on the conversation you just had. The user has been discussing a design, architecture decision, or code change with you, and now wants to queue it as an asynchronous task.
Available Templates
These are the task templates available for use with tsk add -t <template>:
!`tsk template list`
To see the full content of a template, run tsk template show <template>. When a task is created, the {{PROMPT}} placeholder in the template is replaced with whatever you pipe in via heredoc or pass via the -p flag, and any YAML frontmatter is stripped. The result is what gets sent to the agent.
Your Job
-
Summarize the agreed-upon work: Review the conversation above and identify:
- What change or feature was discussed
- Key design decisions that were made
- Any specific files, components, or areas mentioned
- Acceptance criteria or requirements that were established
- Ask clarifying questions about requirements, architecture choices, or task details
- Only proceed once agreement has been reached
-
Create a task name: Come up with a short, branch-friendly name (e.g.,
add-auth,refactor-api,fix-validation) -
Pick the best template: Based on the nature of the task, choose the template from the list above that best matches the work to be done (e.g.,
featfor new features,fixfor bug fixes,refactorfor restructuring,docfor documentation). -
Write the task prompt: Create a clear, self-contained prompt that includes:
- The goal of the change
- Key design decisions from the conversation
- Specific files or areas to focus on (if discussed)
- Acceptance criteria
-
Queue the task: Use
tsk addto create the task:- If you have already written a plan markdown file, prefer using
--prompt-file - If you do not already have a plan in a file, prefer piping in the input
- If you have already written a plan markdown file, prefer using
tsk add -t <template> -n "<task-name>" <<'EOF'
<task description>
EOF
# Alternatively:
tsk add -t <template> --prompt-file <path_to_the_plan>
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.
- 1mo ago First seen · 110 lines · 16 tokens per session scan A 43b505802cea
tsk-add is a skill published in the GitHub repository dtormoen/tsk-tsk (171 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 964 once invoked, about $0.0001 per session on Opus 5.5. 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
loom-usage
Meta-orchestration skill for Claude driving loom itself.
intake
The planning front-door. Captures feature ideas and bugs as graded rows in the root INTAKE.md ledger. Use it when the user says "log an idea", "capture a bug", "add to the backlog", "note this down", "track this feature", or invokes /intake. Owns the requirements interview — fleshes out thin ideas, proactively…
msg
Root menu for msg skills, plus harness modes. --init is the one-time project bootstrap — use it when the user says "initialise project", "bootstrap repo", "set up the framework", "start a new project", or asks to set up project structure in an empty repo. Other modes: --init-staging (add a staging branch), --update…
plan-em
Engineering Manager skill. Reads an approved PRD, runs pre-flight checks against AHA.md, GLOSSARY.md and ARCHITECTURE.md, auto-runs plan-review certification inline (no ask), identifies specialist agents to activate (roster approval — the single human gate), spins them up to write engineering sections directly into…
plan-review
Staff PM contract certifier. Reads an existing PRD and runs a fixed seven-check certification — each check tied to a named downstream consumer (regression authoring, pre-merge's PRD-consistency gate, the safety pauses, eng --build's row/ticket reads). Product tune (--product) runs checks 1/2/3/6; eng tune (--eng) runs…
trello
Manage Trello boards, lists, and cards via the Trello REST API.