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-security-reviewgit 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-security-review)<a href="https://agentmods.dev/skills/hani-q/qstack/qstack-security-review"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-security-review/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-security-review"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-security-review.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 | $0.00110 | $0.01517 |
| Opus 5.5 | $0.00044 | $0.00607 |
| Sonnet 5.5 | $0.00022 | $0.00303 |
| Haiku 4.5 | $0.00011 | $0.00152 |
Grade A, and why
qstack-security-review 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 22d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qstack-security-review
Find security defects an attacker can reach, then report them with evidence, severity, and a score that is arithmetic over the findings. Nothing here probes a deployed system: every check reads source or runs locally against fixtures.
Resolve the scope
Take the scope the way /qstack-review does: a named pull request, a branch
against its merge base, or otherwise the working tree, naming the exact commit
before reading anything. Those are change reviews. One more scope is an audit:
a named directory, or the whole repository when the user asks for an audit
rather than a review of a change. Everything under it is in scope, and the
commit is HEAD plus whether the tree is dirty.
Discover what is installed
Run ../qstack/scripts/installed-skills, which ships with the /qstack skill
beside this one, and keep the rows whose collection is Cloudflare or
Trail of Bits. Each row is collection<TAB>name<TAB>path<TAB>description.
Only skills the skills.sh lock file attributes to those two sources are
listed; a same-named skill from elsewhere is not, because this file cannot
vouch for what it does.
Ask what to run
The built-in diff review always runs. Ask one question, every run, through the
question tool when the host has one and as a numbered list otherwise, offering
each row the script printed and letting the user pick more than one. Condense
each description to a line of about twelve words so the choice reads quickly.
When the script printed no rows, say that no security collection is installed,
name install --with-security-audit and install --with-trail-of-bits, and
continue without asking.
Two notes belong beside a name, because picking it blind wastes a run:
- Cloudflare
security-auditruns in guidance mode for a change review and offers its full audit for an audit scope. Say which the scope selects. - Trail of Bits
entry-point-analyzeris built for an audit scope and adds little to a change review.sarif-parsingneeds a SARIF file from a scanner already run; without one there is nothing for it to read.
What ships with it
2 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.
- 22d ago First seen · 137 lines · 110 tokens per session scan A 5ca179bc4041
qstack-security-review is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 3d ago), licensed MIT. It adds 110 tokens to every session and 1,517 once invoked, about $0.0004 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 2026-10-07.
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…