AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Bug Reporter

skill-firstp1ck-pi-coding-agent-forge-bug-reporter · by Firstp1ck

Agents should invoke this skill when defects, regressions, failed tests, unexpected behavior, or spec mismatches are found. Produces structured reproducible bug reports with severity, evidence, environment, and actionable next steps.

No reviews yet
0 installs
29 views
0.0% view→install

Install

$ agentstack add skill-firstp1ck-pi-coding-agent-forge-bug-reporter

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-firstp1ck-pi-coding-agent-forge-bug-reporter)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Bug Reporter? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Bug Reporter

Produce clear, actionable, reproducible bug reports.

Bug Report Template

Every bug report follows this exact structure:

## BUG-: 

**Severity:** Blocker / Critical / Major / Minor
**Module:** 
**Spec Reference:** 
**Found During:** 

### Reproduction Steps

**Preconditions:**
- [Required state, configuration, or setup]

**Steps:**
1. [Exact step]
2. [Exact step]
3. [Exact step — this triggers the bug]

### Expected Result

[What the spec says should happen, with spec section reference]

### Actual Result

[What actually happens]

**Evidence:**
- Error message: ``
- Log output: ``
- Test output: ``

### Environment

- OS: [if relevant]
- Runtime: [Node version, Rust toolchain, Python version]
- Configuration: [relevant config settings]
- Database state: [if relevant]

### Analysis

**Likely root cause:** [Brief assessment if obvious, "Unknown" if not]
**Related bugs:** [BUG-XXX if related]
**Workaround:** [If one exists, describe it. Otherwise "None known."]

Severity Classification

Blocker

  • Application crashes or won't start
  • Data loss or corruption
  • Core user flow completely broken (can't login, can't save)
  • Security bypass (flag to Zero as well)

Critical

  • Major feature doesn't work
  • No workaround available
  • Affects majority of users
  • Spec requirement completely unmet

Major

  • Feature partially broken
  • Workaround exists but is inconvenient
  • Affects specific user scenarios
  • Edge case in a core flow

Minor

  • Cosmetic or display issue
  • Typo in user-facing text
  • Non-critical edge case
  • Unexpected but harmless behavior

Bug Numbering

Within a QA pass, bugs are numbered sequentially: BUG-001, BUG-002, etc. If re-testing after fixes, new bugs continue the sequence (BUG-005, BUG-006). Fixed bugs keep their original number — mark them as FIXED in the report.

Bug Summary Table

At the top of every QA report, include a summary:

| Bug | Severity | Module | Status | Summary |
|---|---|---|---|---|
| BUG-001 | Critical | auth | OPEN | Login fails with valid credentials |
| BUG-002 | Major | profile | OPEN | Avatar upload accepts files > 10MB |
| BUG-003 | Minor | ui | OPEN | Footer overlaps on mobile viewport |

Re-test Protocol

When Forge fixes a bug:

  1. Pull the latest code
  2. Reproduce using the original steps — verify the bug is fixed
  3. Run the related test cases — verify no regressions
  4. Update the bug status: OPEN → FIXED
  5. If the fix introduced a new bug, file it as a new BUG-XXX

Watchdog skill — Structured bug reporting and severity classification

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.