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-gegenpressgit 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-gegenpress)<a href="https://agentmods.dev/skills/hani-q/qstack/qstack-t3-gegenpress"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-t3-gegenpress/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-gegenpress"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-t3-gegenpress.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 | $0.00083 | $0.02989 |
| Opus 5.5 | $0.00033 | $0.01196 |
| Sonnet 5.5 | $0.00017 | $0.00598 |
| Haiku 4.5 | $0.00008 | $0.00299 |
Grade A, and why
qstack-t3-gegenpress 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 19d 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qstack-t3-gegenpress
Gegenpressing: the moment the ball is lost, press to win it back before the opponent settles. Here every unit that lands is pressed by a reviewer from another model family, the executor wins it back, and the press repeats until nothing is left to find.
This is /qstack-slalom with a lineup instead of a worker list, run through
T3 Code's delegate_task, the only path that launches a GPT child from a
Claude thread or the reverse. Before starting, read ../qstack-slalom/SKILL.md
resolved from this file's own path after following any symlink, never from the
repository under review: its two rules, its Split, its unit brief, its
Integrate and verify, its Report, and its Scope and authority all apply here.
This file carries only what differs.
Invocation
/qstack-t3-gegenpress [task]
[task] is free text. When absent, the task is the one settled in the
conversation so far. The lineup is asked fresh every run.
The roles
| Role | T3 role |
Writes | Family rule | Skippable |
|---|---|---|---|---|
| Architect | this thread | nothing | any | no |
| Second opinion | design |
nothing | not the architect's | yes |
| Executor | implementation |
its units | any | no |
| Workhorse | implementation |
its units | any | yes, defaults to the executor |
| Adversary | review |
nothing | not a writer's | yes |
| Final reviewer | review |
nothing | not a writer's, not the adversary's model | yes |
No delegated role may use the architect's exact model, under slalom's rule 1. The family rules filter the options on top of that.
A family is the model's vendor, read from the id prefix: claude-* is one,
gpt-* another, grok-* a third, whichever provider instance serves it. A
reviewer's family may not be among the families that wrote the code it
reviews. That is the one lesson this skill exists for: a model finds
different bugs in another family's code than in its own.
The architect is this thread. It states the approach, splits the task,
triages findings, and decides. Every other role is a delegate_task child.
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.
- 19d ago Changed · +32 lines 902c3994637a
- 20d ago First seen · 223 lines · 83 tokens per session scan A 3e413f5d5022
qstack-t3-gegenpress is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 3d ago), licensed MIT. It adds 83 tokens to every session and 2,989 once invoked, about $0.0003 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 2026-10-09.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…