testing-cycle

A workflow for handling one piece of user testing feedback. It classifies the feedback, asks for confirmation, then fixes it or records it for later and verifies the result.

In plain words
What is it for?
Use it for feedback about crashes, broken behavior, interface issues, missing capabilities, incorrect automated tests, or possible improvements.
Why use it?
It prevents bugs, missing features, test mistakes, and optional improvements from being treated the same way. Confirmation also reduces the risk of changing the wrong thing.

Skill for Claude CodeCodex

Part of the exosuit plugin — 44 skills, 1 command, 9 agents, 10 hooks shipped together

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/joris887/exosuit/testing-cycle
Any agent
npx skills add joris887/exosuit --skill testing-cycle
Clone the repo
git clone --depth 1 https://github.com/joris887/exosuit

Made for: Claude Code, Codex.

Or install exosuit, the plugin that ships this one along with the rest of its 44 skills, 1 command, 9 agents, 10 hooks.

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,045 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 $0.00022 $0.01045
Opus 5 $0.00011 $0.00522
Sonnet 5 $0.00004 $0.00209
Haiku 4.5 $0.00002 $0.00104

Measured 3d ago against content hash d2418f15d240, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

testing-cycle 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 3d 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.

.claude/skills/testing-cycle/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.


testing-cycle

Processing feedback: $ARGUMENTS

Phase 1: Classify Feedback

Analyze the feedback and assign a classification:

Type Indicators Effort
Bug (Critical) Functionality broken, crash, data loss, core feature High
Bug (Minor) UI glitch, cosmetic, edge case, non-blocking Low
Gap Missing feature, expected capability not implemented Backlog
Test Correction Automated test tests wrong behavior, false positive Medium
Enhancement UX improvement, better wording, nice-to-have Varies

Present the classification to the user for confirmation before proceeding.

Show:

  • Feedback: (original, quoted)
  • Classification: [type]
  • Rationale: (why this classification)
  • Proposed action: (what will be done)

Wait for user confirmation. They may reclassify.

Phase 2: Act by Type

Bug (Critical)

  1. Investigate: Find relevant code, understand the root cause
    • Search for related files using the feedback keywords
    • Read the relevant source files
    • Check if there's an existing test covering this behavior
  2. Test first:
    • If a test exists but tests the wrong thing → fix the test first (it should now fail)
    • If no test exists → write a failing test that captures the bug
    • Run the test to confirm it fails
  3. Fix the code: Make the minimal change to fix the bug
  4. Verify tests pass: Run the project's test command (from CLAUDE.md)
  5. Ask user to verify: "Can you verify this fix in the running app?"
  6. Commit: fix(scope): description

Bug (Minor)

  1. Identify the issue in code
  2. Fix the code (minimal change)
  3. Add test only if the behavior is non-trivial or regression-prone
  4. Run the project's test command
  5. Commit: fix(scope): description

Read the full file on GitHub · 124 lines

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. 3d ago First seen · 124 lines · 22 tokens per session scan A d2418f15d240

Subscribe to this mod's changes

testing-cycle is a skill published in the GitHub repository joris887/exosuit (4 stars, last pushed 13d ago), licensed MIT. It adds 22 tokens to every session and 1,045 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

issue-triage

Issue triage: audit open issues, categorize, detect duplicates, cross-ref PRs, risk assessment, post comments. Args: "all" for deep analysis of all, issue numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.

rtk-ai/rtk · 70 tokens

ship

Build, commit, push & version bump workflow - automates the complete release cycle.

rtk-ai/rtk · 16 tokens

pr-review

Batch review des PRs RTK par ordre de complexité croissante (XS → S → M → L). Pour chaque PR : vérifie l'état (conflits, CLA, reviews), lit le diff complet, analyse le code en contexte, présente un résumé avec lien + taille + recommandation. Attend validation explicite avant tout merge. Poste des commentaires…

rtk-ai/rtk · 128 tokens

rtk-triage

Triage complet RTK : exécute issue-triage + pr-triage en parallèle, puis croise les données pour détecter doubles couvertures, trous sécurité, P0 sans PR, et conflits internes. Sauvegarde dans claudedocs/RTK-YYYY-MM-DD.md. Args: "en"/"fr" pour la langue (défaut: fr), "save" pour forcer la sauvegarde.

rtk-ai/rtk · 96 tokens

code-simplifier

Review RTK Rust code for idiomatic simplification. Detects over-engineering, unnecessary allocations, verbose patterns. Applies Rust idioms without changing behavior.

rtk-ai/rtk · 36 tokens

build-teaql-app

Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…

teaql/teaql-agent-kit · 112 tokens