Agent skill

Identify Fragile Systems

by BuilderIO in BuilderIO/agent-native

Nightly refactor review: find the systems the last day's commits hit hardest, use three weeks of history to tell fragile from fast-moving, write a plan per systemic fix, and file deduplicated Jira…

No licenceAuto-check passedTesting & QA

Install Identify Fragile Systems

skills CLI
$ npx skills add BuilderIO/agent-native --skill identify-fragile-systems -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install BuilderIO/agent-native identify-fragile-systems --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/BuilderIO/agent-native.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/identify-fragile-systems .claude/skills/identify-fragile-systems && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
identify-fragile-systems
GitHub stars
7.1k
Token cost
~957 tokens
SKILL.md length
454 words
Files
2 (incl. scripts)
Skills in repo
108
Repo updated
First seen
Licence
None found

At a glance

Nightly refactor review: find the systems the last day's commits hit hardest, use three weeks of history to tell fragile from fast-moving, write a plan per systemic fix, and file deduplicated Jira…

  • Works in 9 steps: Preflight: $H/doctor.ts and… → Collect: $H/collect.ts --run $RUN (24 h… → Triage: $H/analyze.ts --run $RUN. It… → …
  • /identify-fragile-systems
  • SKILL.md covers Hard rules, Steps and Final report
  • Runs TypeScript scripts from its folder

What it does

Identify Fragile Systems is an agent skill from BuilderIO/agent-native. Nightly refactor review: find the systems the last day's commits hit hardest, use three weeks of history to tell fragile from fast-moving, write a plan per systemic fix, and file deduplicated Jira tickets. Use for /identify-fragile-systems or the nightly run. For a single bug report, use investigate-bug instead.

Its SKILL.md is about 960 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/summarize.ts`).

It sits in Testing & QA, covering Planning, QA and bug reports and Refactoring. It works with Jira. The repository describes itself as: A framework for building agentic apps.

When your agent uses it

  • /identify-fragile-systems
  • The nightly run

Example prompts

  • “/identify-fragile-systems”

Requirements

  • Node.js

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

  1. Preflight: $H/doctor.ts and $J/doctor.ts. For a run-link
  2. Collect: $H/collect.ts --run $RUN (24 h window, 21-day lookback).
  3. Triage: $H/analyze.ts --run $RUN. It writes analysis.md and
  4. Dedup early: $J/jira-match.ts --run $RUN. For each hot system
  5. Investigate the unmatched systems in score order. Focus on
  6. Plan: one plan per root problem, which may span several systems.
  7. Record decisions: give every hot system you didn't plan or sight a
  8. File: $J/jira-upsert.ts --plan (a dry run), then add --apply.
  9. Summarize: $S/summarize.ts --run $RUN. Exit 1 means some hot system

What it can do on your machine

Read from SKILL.md and the folder at commit df30cab. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 1 file in scripts/ (TypeScript), which the agent can run.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Identify Fragile Systems loads about 957 tokens when it runs. Until then it costs about 85 tokens; SKILL.md has 454 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~85
When it runs · the whole SKILL.md, loaded when a task matches
~957

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

Without a licence we can't republish the file, so here is its outline and opening line. It has 454 words (~957 tokens).

“Built to run unattended once a day. It strings together four skills, and each step's details live in that skill's SKILL.md:”

— opening of SKILL.md by BuilderIO
name
identify-fragile-systems
user-invocable
true
scope
dev
metadata.internal
true

Read the full SKILL.md on GitHub

Files

SKILL.md and 1 other file (scripts) in .agents/skills/identify-fragile-systems of BuilderIO/agent-native.

  • SKILL.md
  • scripts/summarize.ts

Open the folder on GitHubat commit df30cab

Compare with similar skills

Identify Fragile Systems next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Identify Fragile Systems compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Identify Fragile Systems this skillBuilderIO/agent-native7.1k—~957Automated safety check: PassNone
Dynamo Jira TicketDynamoDS/Dynamo2k—~1.1kAutomated safety check: PassApache-2.0
Quality Engineering Quality AssuranceHoangNguyen0403/agent-skills-standard572—~629Automated safety check: PassMIT
Dev ReportFHIR/fhir-codegen155—~4.1kAutomated safety check: PassMIT
Issue Repliesantoinecellerier/speaker-tuning-to-easyeffects145—~2kAutomated safety check: PassMIT
Generate Test Planopenshift-eng/ai-helpers120—~1.6kAutomated safety check: PassApache-2.0

Similar skills

  • Dynamo Jira Ticket

    DynamoDS/Dynamo

    Create structured Jira tickets for Dynamo from bug reports, failing tests, or feature requests.

    2k GitHub stars~1.1k tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Quality Engineering Quality Assurance

    HoangNguyen0403/agent-skills-standard

    Write or review manual Zephyr test cases with 1-condition-per-TC granularity, ModuleAction on Screen when Condition naming, platform prefix rules, and High/Normal/Low priority classification.

    572 GitHub stars~629 tokensUpdated yesterday
    Testing & QAAuto-check passed
  • Dev Report

    FHIR/fhir-codegen

    Drafts and iterates on local-development bug reports in the role of a staff-level Tech Lead.

    155 GitHub stars~4.1k tokensUpdated 3 days ago
    Testing & QAAuto-check passed
  • Issue Replies

    antoinecellerier/speaker-tuning-to-easyeffects

    Guides triaging GitHub issues and drafting or posting replies in this repo.

    145 GitHub stars~2k tokensUpdated today
    Testing & QAAuto-check passed
  • Generate Test Plan

    openshift-eng/ai-helpers

    Generate a comprehensive manual testing guide from a Jira issue, GitHub PR URLs, or both.

    120 GitHub stars~1.6k tokensUpdated 4 days ago
    Testing & QAAuto-check passed
  • Browser Javascript TDD

    hashgraph-online/awesome-codex-plugins

    Test-drive browser JavaScript behavior with DOM fixtures, test runners, smoke tests, onload timing, selector refactors, and integration tradeoffs with Selenium or end-to-end tests.

    1.3k GitHub stars~797 tokensUpdated yesterday
    Testing & QAAuto-check passed

More from BuilderIO/agent-native

All 108 skills in this repo
  • Bug Trace

    BuilderIO/agent-native

    Find the root cause of a reported bug: take in the report (GitHub issue, Jira ticket, file, or pasted text), trace the failing path hop by hop with each hop's runtime precondition, find the recent…

    7.1k GitHub stars~555 tokensUpdated today
    Auto-check passed
  • Jira Refactor Findings

    BuilderIO/agent-native

    File and track refactor findings in Jira without duplicates: match a run against existing refactor-findings tickets, create tickets from plan files (Pod, label, attached plan, run link), record…

    7.1k GitHub stars~779 tokensUpdated today
    Auto-check passed
  • System History

    BuilderIO/agent-native

    Blobless-safe git and PR history for this repo. An agent skill from BuilderIO/agent-native.

    7.1k GitHub stars~727 tokensUpdated today
    Auto-check passed
  • Actions

    BuilderIO/agent-native

    How to create and run agent actions. An agent skill from BuilderIO/agent-native.

    7.1k GitHub stars~4.5k tokensUpdated today
    Auto-check passed
  • Client Methods

    BuilderIO/agent-native

    Client method surface rules. An agent skill from BuilderIO/agent-native.

    7.1k GitHub stars~1.2k tokensUpdated today
    Auto-check passed
  • Investigate Bug

    BuilderIO/agent-native

    Given a bug report (GitHub issue, Jira ticket, file, or pasted text), find its root cause and decide per symptom whether it is a one-off or one instance of a pattern worth fixing at the root, then…

    7.1k GitHub stars~1k tokensUpdated today
    Auto-check passed

Works with

Categories

Questions about Identify Fragile Systems

What does Identify Fragile Systems do?

Nightly refactor review: find the systems the last day's commits hit hardest, use three weeks of history to tell fragile from fast-moving, write a plan per systemic fix, and file deduplicated Jira…. Identify Fragile Systems is an agent skill from BuilderIO/agent-native. Nightly refactor review: find the systems the last day's commits hit hardest, use three weeks of history to tell fragile from fast-moving, write a plan per systemic fix, and file deduplicated Jira tickets.

When should I use Identify Fragile Systems?

Identify Fragile Systems fits situations like: /identify-fragile-systems; the nightly run.

How do I install Identify Fragile Systems in Claude Code?

Run `npx skills add BuilderIO/agent-native --skill identify-fragile-systems -a claude-code`. Or copy the skill folder (.agents/skills/identify-fragile-systems in BuilderIO/agent-native) into .claude/skills/identify-fragile-systems in your project. Claude Code loads it when a task matches its description.

How do I install Identify Fragile Systems in Codex?

Run `npx skills add BuilderIO/agent-native --skill identify-fragile-systems -a codex`. Or copy the skill folder (.agents/skills/identify-fragile-systems in BuilderIO/agent-native) into .agents/skills/identify-fragile-systems in your project. Codex loads it when a task matches its description.

Can I use Identify Fragile Systems in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add BuilderIO/agent-native --skill identify-fragile-systems -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/identify-fragile-systems, .gemini/skills/identify-fragile-systems, .github/skills/identify-fragile-systems and .opencode/skills/identify-fragile-systems in your project.

What does Identify Fragile Systems need to run?

Going by SKILL.md and its folder, Identify Fragile Systems needs TypeScript for the scripts in its folder. Our summary lists: Node.js.

Does Identify Fragile Systems access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Identify Fragile Systems safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Identify Fragile Systems use?

No licence was found for Identify Fragile Systems or its repository. Without one, default copyright applies: ask the author before reusing or redistributing it.

How many tokens does Identify Fragile Systems use?

About 957 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Identify Fragile Systems?

Skills that share tags, products or a category with Identify Fragile Systems: Dynamo Jira Ticket (DynamoDS/Dynamo, 2k stars), Quality Engineering Quality Assurance (HoangNguyen0403/agent-skills-standard, 572 stars), Dev Report (FHIR/fhir-codegen, 155 stars) and Issue Replies (antoinecellerier/speaker-tuning-to-easyeffects, 145 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Identify Fragile Systems?

BuilderIO (a GitHub organization) maintains it in BuilderIO/agent-native, which has 7,121 GitHub stars. The repository holds 108 skills in this directory. The repository was last updated on October 11, 2026.

Source: BuilderIO/agent-native on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.