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-blast-radiusgit 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-blast-radius)<a href="https://agentmods.dev/skills/hani-q/qstack/qstack-blast-radius"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-blast-radius/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-blast-radius"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-blast-radius.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 | $0.00061 | $0.00667 |
| Opus 5.5 | $0.00024 | $0.00267 |
| Sonnet 5.5 | $0.00012 | $0.00133 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade A, and why
qstack-blast-radius 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 2mo 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QStack blast radius
Find the breakage that a symbol search or diff review would miss. The result is analysis, not permission to edit, commit, push, publish, deploy, or message anyone.
Trace the risk
- Resolve the exact change from the user's files, diff, branch, or recent work. Read the surrounding implementation and repository instructions.
- State the one critical fact the change is safe because of. Use a second fact only when the safety case truly has two independent hinges.
- Follow effects beyond direct callers. Check pinned dependency source and local patches, lifecycle timing, persisted data, wire formats, other languages reading the same bytes, feature flags, generated artifacts, and downstream consumers. Cite real paths and lines. A search with no matches is evidence when its scope is stated.
- Separate confirmed risks from cleared risks. For each confirmed risk, name the failure path, likelihood, impact, and cheapest decisive check.
Prove the critical fact
Push each safety fact as far down this ladder as is practical:
- A claim only.
- Direct source evidence at a real path and line.
- A traced bad case that cannot reach the failure.
- A script or test that executes the real shipped code and fails loudly when the fact is false.
- A reproduction in the running artifact.
Anything below level 4 remains unproven. Say where proof stopped. Do not round a plausible writeup up to a verified conclusion. For analysis-only work, use existing tests or inline, read-only probes. Creating even a temporary proof file requires write authorization. If direct proof is not authorized, keep the fact unproven. Do not mutate production or exercise a destructive path merely to reach a higher proof level.
Report
- What changed, including behavior the diff does not make obvious.
- The critical safety fact, its proof level, and the observed evidence.
- Confirmed risks, ordered by likely cost.
- Cleared risks and the evidence that cleared them.
- The cheapest pre-merge check that catches the meaningful failure.
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.
- 2mo ago First seen · 65 lines · 61 tokens per session scan A a92e2aa6afbc
qstack-blast-radius is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 3d ago), licensed MIT. It adds 61 tokens to every session and 667 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 2026-08-31.
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…