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/imtylerrrrrr/tk/ennpx skills add Imtylerrrrrr/TK --skill engit clone --depth 1 https://github.com/Imtylerrrrrr/TKWrote 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/imtylerrrrrr/tk/en)<a href="https://agentmods.dev/skills/imtylerrrrrr/tk/en"><img src="https://agentmods.dev/badge/skills/imtylerrrrrr/tk/en.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 | $0.00087 | $0.01678 |
| Opus 5 | $0.00044 | $0.00839 |
| Sonnet 5 | $0.00017 | $0.00336 |
| Haiku 4.5 | $0.00009 | $0.00168 |
Grade A, and why
team-kickoff 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Kickoff
Overview
Sets up collaboration governance for teams that develop with coding agents. Three principles:
- Regulate PRs, leave commits free — with squash merge, the main history consists solely of PR titles. This shrinks the enforcement surface from dozens of commits a day to a handful of PRs.
- Rules live in AGENTS.md and nowhere else — every other file is either a pointer or a device (template, repo setting), not a rule.
- Never report success before verifying — a GitHub setting counts as "applied" only after it has been re-read and confirmed.
Out of scope: roadmap/implementation planning, hosting other than GitHub, teams that hand-code without agents. The interview and all generated artifacts follow the user's language.
Procedure
1. Detect — check, don't ask
- Is this a git repo? Default branch name (never assume — it may be
master). ExistingAGENTS.md/CLAUDE.md/GEMINI.md/.github/PULL_REQUEST_TEMPLATE.md gh auth status, remote existence, repository visibility (public/private)
2. Interview — exactly 4 questions, in one batch
① Duration/intensity: hackathon (≤3 days) / regular ② team size ③ commit & PR title language ④ automated releases (semver/changelog) planned?
Never exceed 4 questions. Don't ask what detection (step 1) already knows. Don't turn optional suggestions (e.g. CI checks) into questions — put them in the report under "For humans (optional)".
On re-runs (partial change requests), confirm only the questions whose answers change — read the rest from the existing artifacts (the AGENTS.md rules block). Restoring artifacts missing from a previous run (e.g. an omitted pointer file) is in scope.
3. Decide the mode
| Hackathon | Regular | |
|---|---|---|
| Review approvals | 0 — self-merge allowed | 1 |
| CI PR-title check | none | suggest in report as "For humans (optional)" |
| Commit-level format hooks | none | only if ④ automated releases was chosen |
Common to all modes: squash-only merge, PR title type: description, exactly 5 types feat|fix|docs|refactor|chore, personal-branch commits are unrestricted (WIP welcome). If team size is 1, set approvals to 0. Regulation levels (L1/L2) and type adjudication: references/commit-conventions.md.
What ships with it
9 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.
- references/commit-conventions.md 3.5 KB
- references/enforcement-matrix.md 2.3 KB
- references/github-setup.md 4.3 KB
- templates/agents-section.md 861 B
- templates/CLAUDE.md 11 B
- templates/GEMINI.md 106 B
- templates/PULL_REQUEST_TEMPLATE.md 488 B
- templates/readme-section.md 261 B
- templates/README.md 2.0 KB
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 · 87 lines · 87 tokens per session scan A f6dab8976c57
team-kickoff is a skill published in the GitHub repository Imtylerrrrrr/TK (2 stars, last pushed 2mo ago), licensed MIT. It adds 87 tokens to every session and 1,678 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 2026-08-31.
Other skills, from other repositories
claude-code-dmwork
Connect to DMWork messaging platform as an AI bot via the OpenClaw DMWork adapter plugin.
meeting
Use for /meeting, /meeting sync, /meeting backfill, or a search term — adaptively analyzes a Granola meeting into decisions, findings, actions, and continuity in shared memory.
reflect
Use when the user says 'we decided', 'I realized', or 'that's a pattern' — captures decisions, findings, or patterns in shared memory. Not a private half-baked thought (/note) or cross-referencing (/deep-reflect).
view
Generate a branded HTML artifact from Egregore data (quest, handoff, activity, board, network, or any document) and open it in the browser. Use for /view, 'render this', or 'show me visually'.
dashboard
See your recent sessions, open handoffs, and current work at a glance. Use for /dashboard, checking your personal status — not the team-wide view (/activity).
deep-reflect
Run deep, multi-hop research over org memory to answer a question or cross-reference an insight, with a cited synthesis. Use for /deep-reflect — not one-shot recall (/search) or capturing an insight (/reflect).