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 hani-q/qstack --skill qstack-t3-see-it-outgit clone --depth 1 https://github.com/hani-q/qstackWrote 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/hani-q/qstack/qstack-t3-see-it-out)<a href="https://agentmods.dev/skills/hani-q/qstack/qstack-t3-see-it-out"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-t3-see-it-out/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/hani-q/qstack/qstack-t3-see-it-out"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-t3-see-it-out.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 | $0.00121 | $0.03140 |
| Opus 5.5 | $0.00048 | $0.01256 |
| Sonnet 5.5 | $0.00024 | $0.00628 |
| Haiku 4.5 | $0.00012 | $0.00314 |
Grade A, and why
qstack-t3-see-it-out 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 10d 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 — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qstack-t3-see-it-out
Seeing it out: the team is ahead and closes the game without giving anything away. Here the work is written and the job is to finish it, with no shortcut past the review.
This is the run the user otherwise types as four prompts: /simplify, "open
PRs", /qstack-review using gpt-6.1-sol and make it 5/5, "and merge". This
thread writes every fix. The reviewer is a delegate_task child that reads
and reports, and nothing else.
Invocation
/qstack-t3-see-it-out [PR...] [--reviewer sol|astra|both|<model-id>] [--no-merge] [--skip-simplify]
PR...: pull request numbers or URLs. When absent, the scope is resolved below.--reviewer:solisgpt-6.1-soland is the default.astraisgpt-6-astra.bothruns one of each per round, and a round passes only when both score 5/5. Any other value is a model id from the catalogue.--no-merge: stop each pull request at 5/5 and leave the merge to the user.--skip-simplify: open pull requests without the simplify pass.
Words after the flags that restate them, such as "and I will merge", count as the flag.
Preflight
In one parallel block: call orchestrator_capabilities, call
t3_thread_configuration for this thread, call list_thread_pull_requests,
run gh auth status, and read the instruction files of every repository in
scope. If orchestrator_capabilities is absent after one bounded attempt,
stop: this skill needs T3 Code's delegate_task.
Resolve each reviewer model in the catalogue. It must sit on a provider
instance with canRunChildTask true, and canRunCrossProviderChildTask true
when it is not this thread's instance. Take its select-type reasoning option
and use high, or the nearest level the entry lists. When the model is
missing, or is this thread's own model, ask through the question tool which
catalogue model reviews instead, recommending one from a different vendor
family. A model reviewing its own code misses what another family finds.
What ships with it
1 file 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.
- 10d ago First seen · 280 lines · 121 tokens per session scan A 38b511899b68
qstack-t3-see-it-out is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 3d ago), licensed MIT. It adds 121 tokens to every session and 3,140 once invoked, about $0.0005 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 2026-10-19.
Other skills, from other repositories
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…