Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/upex-galaxy/agentic-qa-boilerplatenpx agentmods add skills/upex-galaxy/agentic-qa-boilerplate/bug-screenshot-annotationWrote 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/upex-galaxy/agentic-qa-boilerplate/bug-screenshot-annotation)<a href="https://agentmods.dev/skills/upex-galaxy/agentic-qa-boilerplate/bug-screenshot-annotation"><img src="https://agentmods.dev/badge/skills/upex-galaxy/agentic-qa-boilerplate/bug-screenshot-annotation/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/upex-galaxy/agentic-qa-boilerplate/bug-screenshot-annotation"><img src="https://agentmods.dev/badge/skills/upex-galaxy/agentic-qa-boilerplate/bug-screenshot-annotation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00287 | $0.01946 |
| Opus 5 | $0.00143 | $0.00973 |
| Sonnet 5 | $0.00057 | $0.00389 |
| Haiku 4.5 | $0.00029 | $0.00195 |
Grade A, and why
bug-screenshot-annotation 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 11d 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Screenshot Annotation
Reference/utility skill (same tier as /playwright-cli): loaded INSIDE the subagent that is already executing a testing stage — it does not spawn agents of its own and has no dispatch strategy. Typical caller: /sprint-testing Stage 2, when a bug found during exploration is visual/positional (see ../sprint-testing/references/exploration-patterns.md §"Bugs found during exploration").
Why 100% local — the security rationale (binding)
An earlier design routed screenshots through external generative image-editing services. Both attempts failed, one dangerously:
- A quota-walled image MCP was simply unavailable (429 across every tier). Not a design problem — just dead.
- A second generative service got hard-blocked by the agent runtime's own data-exfiltration classifier, because QA screenshots carry real product/customer/competitor data and the destination was not a trusted host. Critically, explicit user authorization in chat did not lift the block — and one screenshot had already leaked to the service's public S3/CloudFront bucket before the second attempt was caught.
The standing lesson: QA evidence containing real product or customer data never routes through an external image service, generative or otherwise. This skill sidesteps the risk entirely — everything happens with HTML+CSS rendered by an HTTP server bound to 127.0.0.1, captured by a local browser-automation CLI; nothing leaves the machine. If a genuinely unhandleable case appears (e.g. annotating a photo of physical signage), go back to the user and talk through anonymization first — NEVER quietly pipe a real screenshot to an external service.
Scope
- Input: a raw screenshot that already exists on disk (typically in the ticket's PBI
evidence/folder). This skill overlays shapes; it does not generate or edit images from a text description. - Output: exactly ONE file that counts as evidence — the final rendered annotated PNG, in the ticket's
evidence/folder. The crop and the annotation HTML are Bucket C working files (see../agentic-qa-core/references/evidence-conventions.md§1): session scratchpad only, never referenced from Jira/ATR/bug tickets. - Not for: filing the bug (reporting-templates owns that), plain before/after shots that read clearly raw, photos of physical objects/documents.
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.
- 11d ago First seen · 83 lines · 287 tokens per session scan A b41448c7f13d
bug-screenshot-annotation is a skill published in the GitHub repository upex-galaxy/agentic-qa-boilerplate (21 stars, last pushed 5d ago), licensed MIT. It adds 287 tokens to every session and 1,946 once invoked, about $0.0014 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 2026-08-30.
Other skills, from other repositories
agent-checkpointing
Implement checkpointing for agent recovery, debugging, and replay. Use this skill when building recoverable agents, implementing replay, debugging agent failures, or creating resumable workflows. Activate when: agent checkpoint, agent recovery, resume agent, agent restart, workflow replay, agent debugging, failure…
error-pattern-analyzer
Use this skill when analyzing error patterns in applications. Activate when the user has recurring errors, wants to find root causes of issues, needs to identify systemic problems, is analyzing error logs, or wants to categorize and prioritize bugs.
log-forensics
Use this skill when investigating issues through logs. Activate when the user needs to analyze log files, search for specific events in logs, correlate logs across services, investigate incidents through logs, or extract insights from application logs.
performance-profiler
Use this skill when investigating performance issues. Activate when the user has slow code, needs to find performance bottlenecks, wants to profile application performance, is optimizing response times, or investigating memory usage.
stack-trace-decoder
Use this skill when analyzing stack traces. Activate when the user has a stack trace to understand, needs to decode error traces, wants to find the root cause from a stack trace, is debugging crashes, or needs help interpreting exception traces.
debug-with-ai
Use this skill when debugging code with AI assistance. Activate when the user has a bug, error, unexpected behavior, needs to understand why code isn't working, wants to analyze stack traces, or is troubleshooting issues in their application.