error-patterns

A reference of common coding-agent mistakes involving tools, Git, continuous integration (automated build and test checks), dependencies, and testing. It also explains TDD, a method where you write a failing test before the code that fixes it.

In plain words
What is it for?
Use it when a tool, build, test, Git command, pull request, or CI check fails unexpectedly.
Why use it?
It gives practical checks for diagnosing unexpected failures and avoiding recurring workflow errors such as dirty rebases, rejected pushes, missing packages, and untested changes.

Skill for Claude CodeCodex

Part of the cc-rpi plugin — 13 skills, 18 commands, 2 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/juan294/cc-rpi/error-patterns
Any agent
npx skills add juan294/cc-rpi --skill error-patterns
Clone the repo
git clone --depth 1 https://github.com/juan294/cc-rpi

Made for: Claude Code, Codex.

Or install cc-rpi, the plugin that ships this one along with the rest of its 13 skills, 18 commands, 2 hooks.

Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 876 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 $0.00038 $0.00876
Opus 5 $0.00019 $0.00438
Sonnet 5 $0.00008 $0.00175
Haiku 4.5 $0.00004 $0.00088

Measured 2d ago against content hash e00e99cb4ea0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

error-patterns 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 2d 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.

templates/skills/error-patterns/SKILL.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Error Patterns -- Top 20

#1: Parallel verification kills siblings -- Chain with ; or &&, never parallel Bash calls.

#2: Worktree cwd resets to main repo -- Prefix EVERY command with cd /absolute/path &&.

#3: Pre-commit hook rejection -- Run typecheck/lint BEFORE committing. Fix first.

#8: Tilde in file paths -- Never use ~ in Read/Write/Edit paths. Full absolute.

#9: Push rejected (non-fast-forward) -- Pull with rebase first: git pull --rebase && git push.

#12: Push and forget CI -- Spawn background agent to monitor CI after every push.

#13: Skipping TDD -- Write the failing test FIRST. Red-Green-Refactor.

#16: Dependencies not installed -- Run pnpm install / uv sync before build/test/lint.

#25: No upstream tracking -- First push: git push -u origin branch-name.

#30: PR create before pushing -- Push branch to remote BEFORE gh pr create.

#33: Pull rebase with dirty tree -- Commit before git pull --rebase (hook enforced).

#44: Push --tags pushes ALL tags -- Push specific: git push origin v1.0.0 or --follow-tags.

#45: Fabricated filesystem paths -- Never guess paths. Use Glob/Grep to find files first.

#48: Commit/push to wrong branch -- Run git branch --show-current before every commit.

#49: Sub-agent git conflicts -- Each sub-agent owns different files. Central commit.

#51: CI explosion from parallel pushes -- Batch pushes. One push triggers one CI run.

#56: Merge to main without topology -- Ask: does merging to main deploy to production?

#58: Deploy without preview verification -- CI passing is NOT sufficient. Verify on preview URL.

#59: Improvised production recovery -- Roll back immediately. Never deploy to diagnose.

#62: Supabase migration without local test -- Always supabase db reset locally before db push.

Error Domains

  • Shell & Tools: #1, #2, #8, #16, #17, #22, #24, #36, #45
  • Git: #3, #6, #9, #11, #15, #18, #25, #33, #44, #48, #54, #55
  • GitHub CLI: #4, #10, #20, #23, #30, #31, #32, #35, #39, #52, #53
  • CI & Deployment: #12, #50, #51, #56, #57, #58, #59, #60
  • Python/macOS: #21, #26, #29, #37, #38, #40, #41, #42
  • Supabase: #61, #62
  • Multi-Agent: #19, #49, #63
  • Process: #5, #7, #13, #14, #27, #28, #34, #43, #46, #47, #64

Read the full file on GitHub · 92 lines

Files

What ships with it

1 file 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. 2d ago First seen · 92 lines · 38 tokens per session scan A e00e99cb4ea0

Subscribe to this mod's changes

error-patterns is a skill published in the GitHub repository juan294/cc-rpi (5 stars, last pushed 13d ago), licensed MIT. It adds 38 tokens to every session and 876 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.

Related

Other skills, from other repositories

claude-md-review

Audit a CLAUDE.md file for the patterns that actually degrade Claude Code's output — vagueness, unnamed files, stale facts, and bloat. Use when asked to review, audit, improve, shrink, or fix a CLAUDE.md, and when a project's results feel inconsistent or Claude keeps rediscovering the same context.

wesammustafa/Claude-Code-Everything-You-Need-to-Know · 69 tokens

best-practices

Searchable knowledge base of 152+ programming best practices across 30+ languages and frameworks. BM25-powered search over curated resources from industry leaders (Google, Airbnb, Uber, Mozilla, Shopify, OWASP).

dereknguyen269/programing-best-practices · 0 tokens

common-exploit-verification

Enforce "No Exploit, No Report" policy with PoC construction standards, false-positive filtering, and evidence collection per vulnerability class across backend, frontend, and mobile. Use when validating security findings, constructing exploit proofs, filtering false positives, or writing pentest findings.

HoangNguyen0403/agent-skills-standard · 61 tokens

JavaScript Tooling

Development tools, linting, and testing for JavaScript projects.

HoangNguyen0403/agent-skills-standard · 18 tokens

common-product-requirements

Standardize PRD discovery and drafting for product scope, user outcomes, requirement IDs, and acceptance criteria. Use when creating PRD, product requirements, feature specification, or acceptance criteria plan.

HoangNguyen0403/agent-skills-standard · 44 tokens

common-security-audit

Probe for hardcoded secrets, injection surfaces, unguarded routes, business logic flaws, and platform-specific weaknesses across backend (Node, Go, Java, Python, Rust), frontend (React, Angular, Vue), and mobile (iOS, Android, Flutter) codebases. Use when performing security audits, vulnerability scans, secrets…

HoangNguyen0403/agent-skills-standard · 77 tokens