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 cboone/agent-harness-plugins --skill wtafgit clone --depth 1 https://github.com/cboone/agent-harness-pluginsWrote 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/cboone/agent-harness-plugins/wtaf)<a href="https://agentmods.dev/skills/cboone/agent-harness-plugins/wtaf"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/wtaf/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/cboone/agent-harness-plugins/wtaf"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/wtaf.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 | $0.00046 | $0.02441 |
| Opus 5.5 | $0.00018 | $0.00976 |
| Sonnet 5.5 | $0.00009 | $0.00488 |
| Haiku 4.5 | $0.00005 | $0.00244 |
Grade A, and why
wtaf 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 8d 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 — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WTAF
Tell the user where things stand: what this work is, what has been done, what is waiting on them, and what comes next. The user usually asks after losing the thread: a long agent run, a new day, a compaction, a truncated scrollback, a merge or deploy that happened elsewhere, or several worktrees running at once. The answer has to restore their footing in one screen.
This skill reports; it does not review code quality. For a review of the current branch's changes, use the review-branch skill instead.
Options
The user may provide these inline, and natural phrasing maps to them whether or not a flag was typed:
- --fast (default): Summarize from the conversation in hand and cheap local and GitHub reads.
- --thorough: Also read the history: earlier sessions in this working directory, the branch's full commit history against its plan, PR review threads and issue discussion, sibling worktrees, and project health measured now. Treat "in depth", "review everything", "comprehensive", "the whole picture", or "I've lost track of this whole project" as
--thorough. - Scope: Anything else narrows or widens the subject: an issue or PR number, a plan, a phase or step, "cross-repo", or "this worktree versus
<path>". - Stated facts: Updates such as "1714 is merged", "it's the next day", or "I deployed a bunch since yesterday" are claims to verify, not options.
If both --fast and --thorough are supplied, ask which one the user meant and stop.
Modes
Fast mode is the default. It answers: where does this stand, and what is next? Thorough mode runs every step as written below. Fast mode changes only these stages; the Ground Rules hold in both.
| Stage | Fast | Thorough |
|---|---|---|
| Conversation (step 2) | The current context only, including any compaction summary. | Also earlier sessions for this working directory, read for user and assistant text only. |
| Plans (step 4) | Identify the governing plan and read its step status from headings, checkboxes and notes. | Also check each plan item against the commits since the base. |
| GitHub (step 5) | PR state, review decision, merge state and check rollup; the linked issue's title and state. | Also unresolved review threads, issue comments since the branch started, milestone progress, and deploy state. |
| Tasks and worktrees (step 6) | The session's task list and running background work. | Also sibling worktrees and resource claims, and how they relate to this one. |
| Health (step 7) | Report CI from the PR, labeled as the latest known result. | Run the project's documented non-mutating check and report it as measured now. |
| Output (step 8) | The fast template in ./references/output.md. |
The thorough template in ./references/output.md. |
What ships with it
3 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.
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.
- 8d ago Changed · +1 lines · +13 tokens per session 2de0c7e457e7
- 15d ago First seen · 133 lines · 33 tokens per session scan A b40d347fbb3a
wtaf is a skill published in the GitHub repository cboone/agent-harness-plugins (2 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 2,441 once invoked, about $0.0002 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 2026-10-02.
Other skills, from other repositories
anti-sleep
Keep a Mac awake with caffeinate during long builds, downloads, or supervised automation runs.
onlyswitch-deeplink
Invoke OnlySwitch built-in switches or buttons via deeplink. Use when the user asks to toggle or trigger an OnlySwitch action (e.g. empty trash, keep awake, dark mode, mute, hide desktop, clear clipboard, eject discs, Xcode derived data, and any other built-in switch or button). Resolve the request to the correct…
gmail
Manage Gmail email — drafting, sending, organizing, filters, vacation replies, and inbox analysis.
outlook
Manage Outlook email — drafting, sending, organizing, rules, vacation replies, and inbox analysis.
watcher
Create and manage polling watchers that monitor external services (Gmail, Google Calendar, GitHub, Linear, Outlook) for events and process them with custom action prompts.
change-keybinding
Customize Warp keyboard shortcuts (keybindings, keymappings) by editing the user's keybindings.yaml file. Use when the user asks to remap a key combination, rebind an action, change a shortcut, or remove a default keybinding (e.g. "change ctrl+space to ctrl+s", "rebind the command palette to cmd+p", "remove the…