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 tahirraufkeeyu/software-development-agent-stack--sdas --skill bug-reportgit clone --depth 1 https://github.com/tahirraufkeeyu/software-development-agent-stack--sdasWrote 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/tahirraufkeeyu/software-development-agent-stack--sdas/bug-report)<a href="https://agentmods.dev/skills/tahirraufkeeyu/software-development-agent-stack--sdas/bug-report"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/bug-report.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 5.1 | $0.00065 | $0.01863 |
| Opus 5 | $0.00032 | $0.00932 |
| Sonnet 5 | $0.00013 | $0.00373 |
| Haiku 4.5 | $0.00006 | $0.00186 |
Grade A, and why
bug-report 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 8d 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 — 163 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
Invoke this skill when:
- A QA engineer, developer, or user observes a defect.
- Another skill (performance, accessibility, e2e) detects a regression.
- A support escalation needs to be converted into an engineering-ready ticket.
Do NOT use when: the issue is a feature request (use a different intake); the root cause is already known and a fix is in flight (write a PR instead).
Inputs
observation(required): One-sentence description of what went wrong ("Cart badge count stays at 0 after adding first item").environment(required):os,browserorapp_version,build(git SHA or release tag),device,network(wifi/4g/throttled).
steps(required): Ordered list of user actions, each a single verb phrase.expected(required): What the user expected.actual(required): What the user observed.frequency(required):always|intermittent (N/M)|once.severity(required):blocker|critical|major|minor|trivial.priority(required):P0|P1|P2|P3.attachments(optional): Paths to screenshots, videos, HAR files, console logs.related_tickets(optional): Issue IDs for related / duplicate / blocked-by tickets.workaround(optional): If the user found one.
Outputs
- A Markdown file following
references/bug-report-template.md, saved toreports/bugs/<yyyy-mm-dd>-<slug>.md. - A reproduction verdict:
reproducible|intermittent|not_reproducible. Non-reproducible reports are NOT filed; the skill instead returns a checklist of information to collect. - If the caller has a tracker MCP configured (Jira, Linear, GitHub Issues), a follow-up suggestion to create the ticket with the generated body.
Tool dependencies
Read,Write,Edit.references/bug-report-template.mdfor the template.- Optional: tracker MCP (Linear, Jira, GitHub) for filing; this skill only drafts, never files automatically.
Procedure
- Collect. Validate all required inputs. If any required field is missing, return a targeted question set — do not fabricate.
- Attempt reproduction. If a runnable target is provided (URL + steps), execute the steps (via Playwright MCP or Chrome DevTools MCP) and record the result. If not reproducible after 3 attempts, set verdict
not_reproducibleand list what additional info is needed (network HAR, console log, exact time, user id, feature flags). - Deduplicate. Grep the bug archive (
reports/bugs/) and the tracker (if MCP available) for similar titles / stack traces. Surface duplicates. - Assess severity/priority. Use this rubric:
- Blocker: data loss, security exposure, or a core flow fully broken.
- Critical: core flow broken with no workaround.
- Major: core flow degraded or secondary flow broken.
- Minor: cosmetic, non-blocking.
- Trivial: typo, spacing. Priority combines severity with reach (users affected) and revenue impact.
- Fill the template. Copy
references/bug-report-template.mdand populate. - Attach evidence. Link screenshots/HAR/logs; verify paths exist.
- Suggest workaround. If one exists or can be derived from the steps, include it.
- Return. The Markdown file path and a one-line summary.
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.
- 8d ago First seen · 163 lines · 65 tokens per session scan A ee6035b0220e
bug-report is a skill published in the GitHub repository tahirraufkeeyu/software-development-agent-stack--sdas (18 stars, last pushed 4mo ago), licensed MIT. It adds 65 tokens to every session and 1,863 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 2026-08-30.
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.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
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…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.