shipkit-feedback-bug

A workflow for turning user feedback and bug reports into investigated bug specifications. It records reproduction steps, a possible root cause, impact, severity, and what was learned.

In plain words
What is it for?
Use it to triage feedback, investigate reported problems, write reproducible bug descriptions, assess affected areas, and prepare issues for prioritisation.
Why use it?
It removes the guesswork from deciding whether a report is a bug and how widely it may affect the product. When the code cannot answer an important question, it asks for clarification instead of inventing details.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/stefan-stepzero/shipkit/shipkit-feedback-bug
Any agent
npx skills add stefan-stepzero/shipkit --skill shipkit-feedback-bug
Clone the repo
git clone --depth 1 https://github.com/stefan-stepzero/shipkit

Made for: Claude Code, Codex.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,691 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00036 $0.05691
Opus 5 $0.00018 $0.02846
Sonnet 5 $0.00007 $0.01138
Haiku 4.5 $0.00004 $0.00569

Measured yesterday against content hash 628db32bef37, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

shipkit-feedback-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 yesterday.

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.

install/skills/shipkit-feedback-bug/SKILL.md · 639 lines

How it starts

The opening of the file, as written. The whole thing — 639 lines — stays where its author put it; the contents beside it link to each section on GitHub.

shipkit-feedback-bug - Feedback to Investigated Bug Specs

Purpose: Transform raw user feedback into fully investigated bug specifications with root cause analysis, blast radius assessment, and captured learnings.

Protocol: This skill follows the canonical elicitation protocol defined in install/shared/references/elicitation-protocol.md (the mechanics — marker, state files, resume). The fork-safe path below is this skill's specific application of that protocol.

Calibration: Apply install/shared/references/ground-or-ask-calibration.md (the intelligence — propose vs ask). Ground first: the feedback text, the codebase, and stack.json are the cited signals. Propose the bug spec (repro steps, root cause hypothesis, severity) grounded in those signals, tagged with source; flag low-leverage guesses as guessed. HIGH-LEVERAGE fields to ask when ungrounded: reproduction steps or expected-vs-actual behavior the codebase cannot disambiguate; severity when the classification would change prioritization. Ask those rather than guessing. Low-leverage detail (reporter name, ancillary environment metadata that the stack implies) → propose a flagged default, no pause. Never silently invent an ungrounded root cause or reproduction the investigation cannot support.


When to Invoke

User triggers:

  • "Triage this feedback"
  • "Process these bug reports"
  • "I got user testing feedback"
  • "Here's what testers found"
  • User pastes a dump of feedback from testing

Workflow position:

  • After user testing or beta feedback received
  • Before debugging/fixing begins
  • Creates investigated specs ready for implementation

Prerequisites

Required:

  • Feedback to process (user provides)

Recommended:

  • Stack defined: .shipkit/stack.json (tech context)
  • Codebase indexed: .shipkit/codebase-index.json (faster investigation)
  • Existing specs: .shipkit/specs/active/*.json (avoid duplicates)

Schema Reference:

  • references/output-schema.md - Complete JSON schema definition
  • references/example.json - Realistic bug spec example

Read the full file on GitHub · 639 lines

Files

What ships with it

2 files 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.

Changes

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.

  1. yesterday First seen · 639 lines · 36 tokens per session scan A 628db32bef37

Subscribe to this mod's changes

shipkit-feedback-bug is a skill published in the GitHub repository stefan-stepzero/shipkit (1 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 5,691 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 2026-08-31.