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/qstack-fix-root-causesnpx skills add hani-q/qstack --skill qstack-fix-root-causesgit 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 | $0.00047 | $0.00471 |
| Opus 5 | $0.00023 | $0.00235 |
| Sonnet 5 | $0.00009 | $0.00094 |
| Haiku 4.5 | $0.00005 | $0.00047 |
Grade A, and why
qstack-fix-root-causes 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 2d 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.
What it actually says
Fix root causes
Diagnosis precedes remediation. A request to diagnose is read-only and does not authorize implementing a fix, adding instrumentation, clearing state, or changing every related instance. It also does not authorize commits, pushes, publishing, deployment, or external messages.
Diagnose
- Reproduce the symptom with the smallest faithful path. If it cannot be reproduced, state that limitation and keep the eventual fix unverified.
- Gather the actual error, state, inputs, and timing. Use existing logs and observability first; instrument only when the request authorizes that edit.
- Follow the causal chain by repeatedly asking why each observed condition exists. Stop at the layer whose behavior explains the full reproduction.
- Reject symptom patches such as a nil guard that merely silences a crash or a long comment defending a workaround.
- Search for the same causal pattern across the relevant codebase. Report out-of-scope instances, but modify only the authorized scope.
- For failures that appear only after restart, inspect changing persistent state before unchanged code: configuration, caches, lockfiles, serialized state, and abandoned temporary artifacts. Clearing state can support a diagnosis; it is not itself a durable fix.
Report the reproduction, evidence, causal chain, root cause, pattern scan, proposed repair, and verification path. Implement only when the user's request includes fixing the problem.
Adapted from Lauren Tan's PStack
principle-fix-root-causes
at commit 60c641e4fad674784b30abcf9f8915dea39df38d under the MIT License.
See third-party notices.
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.
- 2d ago First seen · 42 lines · 47 tokens per session scan A 7e3435419dae
qstack-fix-root-causes is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 5d ago), licensed MIT. It adds 47 tokens to every session and 471 once invoked, about $0.0002 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…