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-prove-it-worksgit 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-prove-it-works)<a href="https://agentmods.dev/skills/hani-q/qstack/qstack-prove-it-works"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-prove-it-works/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-prove-it-works"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-prove-it-works.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 | $0.00046 | $0.00457 |
| Opus 5.5 | $0.00018 | $0.00183 |
| Sonnet 5.5 | $0.00009 | $0.00091 |
| Haiku 4.5 | $0.00005 | $0.00046 |
Grade A, and why
qstack-prove-it-works 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 1mo 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
Prove it works
For every completion claim, identify the direct observation that would make it true. Verification does not authorize remediation, deployment, external messages, unsafe live mutations, commits, pushes, or publishing.
Prove the real path
- State the exact claim and the artifact that owns the truth.
- Validate the observation method. When a check disagrees with the system, inspect stale caches, derived views, and faulty probes before choosing which result to trust.
- Build or validate static structure when relevant, but treat that as a prerequisite rather than proof of runtime behavior.
- Run the actual artifact and exercise the feature from input through every boundary to its output. For integrations, test the complete communication path in a safe environment.
- Read actual values and artifacts. Check process liveness directly. Inspect delegated diffs, files, and runtime results instead of accepting summaries.
- Script complex or repeatable comparisons when that makes the evidence deterministic. Keep temporary proof local unless a durable artifact was requested.
Report each claim, check, observed evidence, and result. Mark any segment that
requires unavailable infrastructure or additional authority as UNPROVEN;
do not substitute a proxy. During approved planned work, record durable evidence
in the existing QStack execution.md and create no second audit format.
Adapted from Lauren Tan's PStack
principle-prove-it-works
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.
- 1mo ago First seen · 42 lines · 46 tokens per session scan A 610130e7cdde
qstack-prove-it-works is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 3d ago), licensed MIT. It adds 46 tokens to every session and 457 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
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.