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 gvkhosla/compound-engineering-pi --skill reproduce-buggit clone --depth 1 https://github.com/gvkhosla/compound-engineering-piWrote 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/gvkhosla/compound-engineering-pi/reproduce-bug)<a href="https://agentmods.dev/skills/gvkhosla/compound-engineering-pi/reproduce-bug"><img src="https://agentmods.dev/badge/skills/gvkhosla/compound-engineering-pi/reproduce-bug/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/gvkhosla/compound-engineering-pi/reproduce-bug"><img src="https://agentmods.dev/badge/skills/gvkhosla/compound-engineering-pi/reproduce-bug.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 | $0.00039 | $0.01774 |
| Opus 5 | $0.00019 | $0.00887 |
| Sonnet 5 | $0.00008 | $0.00355 |
| Haiku 4.5 | $0.00004 | $0.00177 |
Grade A, and why
reproduce-bug 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 10d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- reproduce-bug — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reproduce Bug
A framework-agnostic, hypothesis-driven workflow for reproducing and investigating bugs from issue reports. Works across any language, framework, or project type.
Phase 1: Understand the Issue
Fetch and analyze the bug report to extract structured information before touching the codebase.
Fetch the issue
If no issue number or URL was provided as an argument, ask the user for one before proceeding (using the platform's question tool -- e.g., AskUserQuestion in Claude Code, request_user_input in Codex, ask_user in Gemini -- or present a prompt and wait for a reply).
gh issue view $ARGUMENTS --json title,body,comments,labels,assignees
If the argument is a URL rather than a number, extract the issue number or pass the URL directly to gh.
Extract key details
Read the issue and comments, then identify:
- Reported symptoms -- what the user observed (error message, wrong output, visual glitch, crash)
- Expected behavior -- what should have happened instead
- Reproduction steps -- any steps the reporter provided
- Environment clues -- browser, OS, version, user role, data conditions
- Frequency -- always reproducible, intermittent, or one-time
If the issue lacks reproduction steps or is ambiguous, note what is missing -- this shapes the investigation strategy.
Phase 2: Hypothesize
Before running anything, form theories about the root cause. This focuses the investigation and prevents aimless exploration.
Search for relevant code
Use the native content-search tool (e.g., Grep in Claude Code) to find code paths related to the reported symptoms. Search for:
- Error messages or strings mentioned in the issue
- Feature names, route paths, or UI labels described in the report
- Related model/service/controller names
Form hypotheses
Based on the issue details and code search results, write down 2-3 plausible hypotheses. Each should identify:
- What might be wrong (e.g., "race condition in session refresh", "nil check missing on optional field")
- Where in the codebase (specific files and line ranges)
- Why it would produce the reported symptoms
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.
- 10d ago First seen · 195 lines · 39 tokens per session scan A c61767cfa1c6
reproduce-bug is a skill published in the GitHub repository gvkhosla/compound-engineering-pi (51 stars, last pushed 4mo ago), licensed MIT. It adds 39 tokens to every session and 1,774 once invoked, about $0.0002 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
diagnosing-bugs
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.
lsp-validation
Use Language Server Protocol tools for code validation, navigation, and refactoring. Essential for maintaining code quality.
diagnose
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.
manage-skills
A maintenance workflow for checking whether project verification skills still cover the code and rules that changed during a session.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
create-issue
Transitional alias — prefer /prflow:specs, which runs the same issue-drafting pipeline. Use when a rough user story, bug report, feature idea, piece of feedback, or an implementation plan should be recorded as a GitHub issue rather than built right now. This command name is retained so existing /prflow:create-issue…