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/vmobifystudio/app-dev-team/support-miningnpx skills add vmobifystudio/app-dev-team --skill support-mininggit clone --depth 1 https://github.com/vmobifystudio/app-dev-teamWrote 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/vmobifystudio/app-dev-team/support-mining)<a href="https://agentmods.dev/skills/vmobifystudio/app-dev-team/support-mining"><img src="https://agentmods.dev/badge/skills/vmobifystudio/app-dev-team/support-mining.svg" alt="Measured on agentmods" 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 | $0.00055 | $0.00627 |
| Opus 5 | $0.00028 | $0.00313 |
| Sonnet 5 | $0.00011 | $0.00125 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
support-mining 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 today.
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.
Support mining
Users describe symptoms, in their own words, having already worked around the problem. This is the pass that turns that into something the board can act on — and the discipline that keeps it from becoming a list of the loudest complaints.
Sources, and what each is good for
| Source | Good evidence for | Systematically biased toward |
|---|---|---|
| Store reviews | first-run and pricing friction | the delighted and the furious, never the middle |
| Support threads | reproducible defects | users willing to write in — a small, patient minority |
| Crash clusters | the truth about stability | devices and OS versions you have most of |
| Uninstall / churn signals | where value failed to land | nothing at all about why |
Name the bias in the report. A finding from reviews alone is a finding about reviewers.
The pass
- Cluster by user-described symptom, not by your guess at the cause. "Photos disappeared" and "lost my edits" may be one defect or three; keep them separate until evidence merges them.
- Rank by
frequency × severity × recency, and show all three columns. A cluster ranked by volume alone buries the data-loss report mentioned twice. - Attach evidence to each cluster — verbatim quotes with dates, app version, device and OS where available. A cluster with no verbatim is your paraphrase, and you label it as such.
- Separate a defect from a missing feature from a misunderstanding. All three arrive as "it
doesn't work" and they route to three different people. A misunderstanding is a
content-designfinding, not a bug. - Check each cluster against
knowledge/failure-corpus.md. A cluster matching a known class that already has a shipped rule is a recurrence — the rule did not work, and that is a strictly more valuable finding than the incident.
The rules
- Never fabricate or paraphrase a quote into something cleaner. Verbatim or nothing.
- A cluster is not a ticket. Hand
qa-engineera reproduction attempt; a bug filed from a review without one wastes a developer's day. - Report what you could not tell. Reviews rarely say version or device; guessing which release regressed is how a good release gets rolled back.
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.
- today First seen · 51 lines · 55 tokens per session scan A 65314fad698a
support-mining is a skill published in the GitHub repository vmobifystudio/app-dev-team (4 stars, last pushed 24d ago), licensed MIT. It adds 55 tokens to every session and 627 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
execute-task
Implement one task (or a cohesion bundle) from a signed-off spec (Ready or Active): recompute the execution freshness gate, write the verifying test first, implement to green, run the project's full CI with adaptive retry, converge via the configured reviewsequence (default /polish --nested), then open a draft PR…
builder
Detect a project's stack and recommend or apply the universal mechanical quality guards from planwright's core catalog (formatter, linters, type-checker, test runner, secret scan, commit hooks, CI gate), plus the growable breadth dimensions. Escalates stake-bearing decisions (auth, data modeling, security posture…
spec-walkthrough
Render a spec bundle (or a chosen slice) into a plain-language, didactic comprehension artifact a human reads and judges for themselves: an unaided cold read before kickoff, re-orientation mid-execution, or onboarding to a finished or abandoned spec. Standalone and strictly read-only: it renders any status, never…
drain
Run the on-demand drain pass over every spec bundle's Gate deferral entries: evaluate structured GATE(when:) conditions, surface date and free-text gates, report malformed ones, inventory each live bundle's [manual] test-spec entries, and surface the observations log's unmined state. Read-only; nothing is…
orchestrate
Advance one planwright spec by one step: pick the next ready unit critical-path-first (or a cohesion bundle), run the freshness gate, record the dispatch under the per-spec lock, and dispatch /execute-task via the backend. A stateless, disposable control tower; a reconcile sweep rebuilds from disk. Never merges, marks…
spec-kickoff
Walk a spec bundle section by section to mutual understanding, producing the signed-off kickoff brief downstream skills execute from. On sign-off: runs the Discovery-Rigor lens pass, flips Draft to Ready, records the sign-off record (anchor last), commits, pushes, opens a draft PR, then on clean completion marks the…