Skip to content
Skills Library
Programming · Review & audit

bug-echo

/bug-echo

After a bug fix, find and rate other instances of the same defect. Infer and validate a pattern from the fix or use a supplied description, then classify each match against current code. Use for "run bug-echo", "echo this fix", "scan for similar bugs", "find other instances", or an "after-fix scan"; not a general bug hunt without a fix or described pattern.

Repository
bug-echo ↗
Licence
Apache-2.0
Last repository change
19.10.2026

Assessment and security

100/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content35 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
8
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 19.10.2026, without references to retired models or APIs.

Licence

Apache-2.0, otwarta: można używać i zmieniać, z zachowaniem licencji i informacji o zmianach.

What it does and when to use it

After a bug fix, find and rate other instances of the same defect. Infer and validate a pattern from the fix or use a supplied description, then classify each match against current code. Use for "run bug-echo", "echo this fix", "scan for similar bugs", "find other instances", or an "after-fix scan"; not a general bug hunt without a fix or described pattern.

Triggers from the description

run bug-echoecho this fixscan for similar bugsfind other instancesafter-fix scan
Original author description

After a bug fix, find and rate other instances of the same defect. Infer and validate a pattern from the fix or use a supplied description, then classify each match against current code. Use for "run bug-echo", "echo this fix", "scan for similar bugs", "find other instances", or an "after-fix scan"; not a general bug hunt without a fix or described pattern.

How it works

  1. Runtime and scope
Original SKILL.md headings · 40 lines, 424 words
SKILL.md preview
---
name: bug-echo
description: 'After a bug fix, find and rate other instances of the same defect. Infer and validate a pattern from the fix or use a supplied description, then classify each match against current code. Use for "run bug-echo", "echo this fix", "scan for similar bugs", "find other instances", or an "after-fix scan"; not a general bug hunt without a fix or described pattern.'
license: Apache-2.0
metadata:
  version: 1.8.0
  author: Terry Nyberg, Coffee & Code LLC
  tier: execution
  category: debugging
---

# bug-echo

Find sibling instances of a bug the user just fixed, or of a pattern they describe.
Read [WORKFLOW.md](WORKFLOW.md) and perform its scan, classification, and reporting procedure.
Read linked examples only when relevant. Both Codex and Claude Code use these same files.

For a `--version` request, report the version above and the actual loaded skill path, then stop.

## Runtime and scope

- **Invocation:** Codex uses `$bug-echo`; Claude Code plugins use `/bug-echo:bug-echo`
  (or the command listed by that installation). A manual Claude skill uses `/bug-echo`.
  Plain-language requests work in either app. These are assistant requests, not shell commands.
- **Tools:** Names such as Read, Write, Edit, Bash, Grep, Glob, and Agent in the procedure
  describe operations. Use the tools actually available in the current app; prefer `rg`
  and `rg --files` for shell searches. Do not call nonexistent Claude tools from Codex.
  Use the app's question interface or ordinary conversation for necessary clarification.
- **Resources:** Resolve bundled links from this skill's directory, not the project's
  working directory. Companion skills are optional; never claim an absent skill ran.
- **Authorization:** A clear request to scan authorizes that scan. Ask only about material
  ambiguity. Report-only requests do not authorize fixes or commits. When fixes or commits
  are already requested, carry that authorization forward without asking for each edit.
- **Baseline:** A dirty tree does not block a read-only scan. Preserve unrelated changes.
  Validate inferred patterns against the actual old side: HEAD for a staged diff, the
  index for an unstaged diff, and the selected commit's parent for a commit diff.
- **Current evidence:** Read current code before classifying. A prior fix commit is not
  evidence that a current match is still fixed. Keep candidate and precondition patterns
  separate, and label approximate preconditions as the procedure requires.
- **Reports:** Use the labels BUG, WATCH, OK, OK (CANON), and REVIEW. When a correct
  site is cited as the reference to copy, label it **OK (CANON)** explicitly. Give BUG
  and WATCH findings the procedure's six ratings and their own user impact. Describe
  unobserved consequences conditionally; do not claim data loss, rendered UI behavior,
  or runtime verification that the available code and checks do not establish.
- **Batching:** Above 500 files, use sub-agents only when supported and allowed. Otherwise
  run the same batches locally with the same aggregation contract and report the fallback.
- **Outputs:** Honor the user's destination and workspace permissions. The default report
  location is `.agents/research/`; in a projectless Codex chat use its writable outputs
  directory. A report's existence does not prove its findings were fixed or verified.
Files in this package (8)
  • SKILL.md 3 KB
  • WORKFLOW.md 50 KB
  • agents/openai.yaml 1 KB
  • examples/2026-05-03-bug-echo-deep-viewbuilder-crash.md 19 KB
  • examples/canon-reference-implementation.md 8 KB
  • examples/describe-mode-await-in-forEach.md 12 KB
  • examples/large-codebase-hardening-rationale.md 8 KB
  • examples/recon-scout-rationale.md 6 KB

Versions

The database has no other skills named bug-echo.

Database snapshot: 13.11.2026 · package version 4bf05cad2a6e (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 100ai-bug-fix-triage
    Triage JIRA bugs against repository code to classify AI fixability. Use when reviewing a backlog of bugs to determine which ones an AI agent can fix.
  • 100echo
    Echo framework guardrails, patterns, and best practices for AI-assisted development. Use when working with Echo projects, or when the user mentions Echo framework. Provides middleware patterns, routing, context handling, and REST API guidelines.
  • 100go-echo
    Echo is a minimalist, high-performance Go web framework for REST APIs, with a fast router, route groups, middleware, request binding and validation, and centralized error handling. Use when asked to build a Go API with Echo, add JWT auth, CORS, rate limiting or request logging…
  • 100hatch3r-bug-fix
    Step-by-step bug fix workflow. Diagnose root cause, implement minimal fix, write regression test. Use when fixing bugs, working on bug report issues, or when the user mentions a bug.
  • 100bug-hunter
    Use this skill when scanning source code for bugs, anti-patterns, code smells, or quality issues in a codebase, or when running a proof-driven bug hunt that must find, prove, fix, and verify one real defect. Trigger on the explicit vocabulary — "bug", "bug hunt", "/bughunt",…
  • 100echo
    Echo Go web framework. Covers routing, middleware, binding, context, and WebSocket. Use for high-performance, minimalist Go APIs. USE WHEN: user mentions "echo", "labstack echo", "go echo framework", asks about "echo middleware", "echo context", "echo binding", "echo websocket",…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.