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 agentmods add skills/hani-q/qstack/qstacknpx skills add hani-q/qstack --skill qstackgit clone --depth 1 https://github.com/hani-q/qstackWhat 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 | $0.00073 | $0.01166 |
| Opus 5 | $0.00036 | $0.00583 |
| Sonnet 5 | $0.00015 | $0.00233 |
| Haiku 4.5 | $0.00007 | $0.00117 |
Grade A, and why
qstack scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/qstack
Show what is installed, then what to run next. Nothing is stored in this file: every run reads the skills on disk at that moment, so a skill added or a collection installed yesterday appears today.
1. Read the installed skills
Run this once. It prints one row per skill as collection<TAB>name<TAB>description.
python3 - <<'PY'
import json, os, re
home = os.path.expanduser("~")
lock = os.path.join(home, ".agents", ".skill-lock.json")
sources = {}
if os.path.isfile(lock):
for name, entry in json.load(open(lock)).get("skills", {}).items():
sources[name] = entry.get("source", "")
COLLECTIONS = {"mattpocock/skills": "Matt Pocock"}
def description(path):
lines = open(path, encoding="utf-8").read().splitlines()
if not lines or lines[0] != "---":
return ""
out, folded = [], False
for line in lines[1:]:
if line == "---":
break
if folded:
if line[:1].isspace():
out.append(line.strip())
continue
break
m = re.match(r"^description:\s*(.*)$", line)
if m:
value = m.group(1).strip()
if value in ("", ">", "|", ">-", "|-"):
folded = True
else:
return value.strip('"')
return " ".join(out)
seen, rows = set(), []
for d in (".claude/skills", ".codex/skills", ".agents/skills"):
root = os.path.join(home, d)
if not os.path.isdir(root):
continue
for name in sorted(os.listdir(root)):
md = os.path.join(root, name, "SKILL.md")
if name in seen or not os.path.isfile(md):
continue
if name == "qstack" or name.startswith("qstack-"):
group = "qstack"
elif name == "human-review":
group = "human-review"
elif sources.get(name) in COLLECTIONS:
group = COLLECTIONS[sources[name]]
else:
continue
seen.add(name)
rows.append((group, name, description(md)))
order = {"qstack": 0, "human-review": 1}
for group, name, desc in sorted(rows, key=lambda r: (order.get(r[0], 2), r[0], r[1])):
print(f"{group}\t{name}\t{desc}")
PY
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.
- yesterday First seen · 133 lines · 73 tokens per session scan A fcf2404485d1
qstack is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 5d ago), licensed MIT. It adds 73 tokens to every session and 1,166 once invoked, about $0.0004 per session on Opus 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…