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-make-operations-idempotentgit 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-make-operations-idempotent)<a href="https://agentmods.dev/skills/hani-q/qstack/qstack-make-operations-idempotent"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-make-operations-idempotent/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-make-operations-idempotent"><img src="https://agentmods.dev/badge/skills/hani-q/qstack/qstack-make-operations-idempotent.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 | $0.00052 | $0.00593 |
| Opus 5.5 | $0.00021 | $0.00237 |
| Sonnet 5.5 | $0.00010 | $0.00119 |
| Haiku 4.5 | $0.00005 | $0.00059 |
Grade A, and why
qstack-make-operations-idempotent 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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Make operations idempotent
An idempotent operation converges from any state a previous attempt could have left behind. A duplicate request that merely happens not to fail is not enough.
Test convergence
- List every durable mutation and external side effect in execution order.
- Model two consecutive runs from the completed state. When verification is authorized in a safe environment, run both and compare the real end state, not only the exit code.
- Model a crash after every mutation point and the rerun from each partial state. Fault-inject only under the verification authority described below.
- Include stale locks, abandoned temporary files, live sessions, regenerated input, reordered records, and content-equivalent artifacts where relevant.
- Add reconciliation before mutation whenever leftover state changes the next run's result. Prefer adoption, content comparison, atomic replacement, single ownership, and stale-owner detection over creation-order guesses.
- Prove repeated and resumed runs satisfy the same domain invariants. Generated identifiers or timestamps need not be byte-identical unless the domain requires that.
Report the mutation map, failure points tested, stale-state policy, convergence proof, and any unresolved case. Never clear or overwrite user data merely to make a retry pass without explicit authority for that destructive behavior. Before reclaiming a lock or live session, prove ownership and liveness.
A design or review request is analysis-only: it does not authorize executing a mutating operation, injecting a crash, creating a disposable environment, or causing external side effects. Run repeated or partial-failure tests only when the request authorizes verification and the environment is disposable and safe. Live or external effects such as charges, messages, database writes, or process interruption require explicit authority for those exact effects. When direct proof would exceed that authority, report the case as UNPROVEN. Analysis alone also does not authorize edits, commits, pushes, publishing, deployment, or external messages.
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 · 51 lines · 52 tokens per session scan A 55ebc9b5ddbf
qstack-make-operations-idempotent is a skill published in the GitHub repository hani-q/qstack (7 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 593 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
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
cwv-optimizer
Diagnose and fix Core Web Vitals issues on AEM Edge Delivery Services pages. Goes deeper than generic CWV advice by understanding EDS-specific performance patterns including the 100KB LCP budget, E-L-D loading phases, block rendering behavior, and third-party script impact. Produces specific fixes for LCP, CLS, and…
incident-response-incident-response
Coordinate production incident triage, mitigation, investigation, recovery, and follow-up. Use when responding to outages or other incidents that require structured operational coordination.
ci-fixer
CI failures - read error, minimal fix, verify.