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.
npx skills add cognitedata/builder-skills --skill correctness-and-error-handlinggit clone --depth 1 https://github.com/cognitedata/builder-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cognitedata/builder-skills/correctness-and-error-handling)<a href="https://agentmods.dev/skills/cognitedata/builder-skills/correctness-and-error-handling"><img src="https://agentmods.dev/badge/skills/cognitedata/builder-skills/correctness-and-error-handling/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cognitedata/builder-skills/correctness-and-error-handling"><img src="https://agentmods.dev/badge/skills/cognitedata/builder-skills/correctness-and-error-handling.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 148 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00102 | $0.03165 |
| Opus 5 | $0.00051 | $0.01582 |
| Sonnet 5 | $0.00020 | $0.00633 |
| Haiku 4.5 | $0.00010 | $0.00316 |
Grade A, and why
correctness-and-error-handling 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 10d 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.
How it starts
The opening of the file, as written. The whole thing — 365 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Correctness & Error Handling Fix
Find and fix correctness issues and missing error handling in $ARGUMENTS (or the whole app if no argument is given). Work through every step below. Each step searches for problems and then fixes them in place. Only report issues that cannot be auto-fixed.
Step 1 — Map data flows and fix known defects
Read these files before checking anything:
src/main.tsx/src/App.tsx— top-level error boundaries and auth flow- All files matching
**/hooks/*.ts,**/contexts/*.tsx— shared async state - All files matching
**/api/*.ts,**/services/*.ts— CDF SDK call sites
For each async data source, note:
- What happens when the request fails (network error, CDF 403, timeout)?
- What does the UI show while loading?
- What does the UI show if the result is empty?
Find and fix known defects in critical paths
# Find TODO/FIXME/HACK in critical code paths (not test files)
grep -rn --include="*.ts" --include="*.tsx" -E "(TODO|FIXME|HACK|XXX):" src/ | grep -v ".test." | grep -v ".spec."
# Find "fix" or "broken" or "workaround" markers
grep -rn --include="*.ts" --include="*.tsx" -i -E "(TODO.*fix|workaround|broken|known.?bug|temporary.?hack)" src/
For each match in a critical path (data fetching, rendering, auth, navigation):
- Read the surrounding code to understand the incomplete/broken behavior.
- Fix the underlying issue — implement the missing logic, correct the broken behavior, or add proper error handling.
- If the fix requires significant architectural changes beyond this skill's scope, replace the TODO with a safe failure mode: graceful error handling, a sensible fallback value, or an explicit user-facing message explaining degraded functionality.
- Remove the TODO/FIXME/HACK comment after fixing. The code should speak for itself.
Do not leave TODOs in critical paths. Every one must be resolved or converted to a safe fallback.
Step 2 — Add top-level error boundary
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.
- 10d ago First seen · 365 lines · 102 tokens per session scan A 776bca56c44e
correctness-and-error-handling is a skill published in the GitHub repository cognitedata/builder-skills (6 stars, last pushed 3d ago), licensed Apache-2.0. It adds 102 tokens to every session and 3,165 once invoked, about $0.0005 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.
Other skills, from other repositories
debug-optimize-lcp
Guides debugging and optimizing Largest Contentful Paint (LCP) using Chrome DevTools MCP tools. Use this skill whenever the user asks about LCP performance, slow page loads, Core Web Vitals optimization, or wants to understand why their page's main content takes too long to appear. Also use when the user mentions…
systematic-debugging
Use when debugging a failing test, build error, or runtime issue that isn't immediately obvious. Guides a 4-phase root cause analysis instead of random fix attempts.
diagnose
Trace from a reproduced symptom to the source code that causes it. Pin the specific file and approximate line, rate confidence in the cause and clarity of the fix independently, and always propose a concrete fix.
repro-admin
Reproduce an EmDash admin UI bug. Attach a container, start the demo dev server, drive the admin with agent-browser using the dev-bypass session, and capture the reproduction as screenshots plus a replayable transcript.
log-error-digest
Analyze log files to troubleshoot errors, identify peak error periods, and produce error clustering, frequency statistics, and time distribution reports. Supports JSON, syslog, and Nginx formats with automatic detection. Use when a user uploads a .log file and asks to analyze errors, find patterns, debug issues, or…
byted-util-volcengine-detect-retry
An orchestration workflow for Volcengine Cloud Detect, a service that checks websites or network endpoints from test locations.