agent-quick-reference

A compact reference card for an agent workflow called APEI: analyze the problem, plan the smallest useful steps, execute and test each step, then iterate. It also includes templates for task plans, error reports, progress updates, and selecting reasoning modes.

In plain words
What is it for?
Use it to structure bug fixes, feature work, debugging, testing, commits, progress updates, and decisions about how much reasoning or context to use.
Why use it?
It keeps routine coding work focused and makes the problem, affected files, verification method, errors, and progress easier to track.

Agent

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 agents/rtur2003/claude-code-promts-skills/agent-quick-reference
Clone the repo
git clone --depth 1 https://github.com/Rtur2003/Claude-Code-Promts-Skills
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,212 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 $0.00000 $0.01212
Opus 5 $0.00000 $0.00606
Sonnet 5 $0.00000 $0.00242
Haiku 4.5 $0.00000 $0.00121

Measured 3d ago against content hash 846aa6dc0642, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-quick-reference 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.

prompts/english/agents/agent-quick-reference.md · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Quick Reference Card

Token-Optimized Cheat Sheet | Copy & Use


🔄 Core Loop: APEI

A → ANALYZE: What's the problem? What exists?
P → PLAN: Minimal steps to solve?
E → EXECUTE: One step → test → commit
I → ITERATE: Optimal? If not → A

📋 Templates

Analysis Summary

**Problem**: [1 sentence]
**Stack**: [lang/framework]
**Files**: [affected files]
**Success**: [measurable criteria]

Task Plan

**Step 1**: [action] → Files: [x,y] → Test: [how]
**Step 2**: [action] → Files: [x,y] → Test: [how]

Error Report

**Error**: [type] at [file:line]
**Cause**: [root cause]
**Fix**: [solution]
**Verify**: [test command]

Progress Update

✅ Done: [completed tasks]
🔄 Now: [current task]
⏳ Next: [upcoming tasks]

🔧 Claude Code Modes

/compact    → Fast, minimal tokens (simple tasks)
/think      → Extended reasoning (complex logic)
/ultrathink → Max depth (architecture, security)
/clear      → Reset context (between tasks)
/cost       → Check token usage
/memory     → View/edit CLAUDE.md
/init       → Initialize project CLAUDE.md

Mode Selection

Simple fix/rename    → /compact
Standard feature     → Normal (default)
Complex algorithm    → /think
Critical decision    → /ultrathink

💻 Commands

Discover Project

tree -L 3 -I 'node_modules|dist|.git'
cat package.json | head -30
git log --oneline -10

Validate Changes

# JS/TS
npm test && npm run lint && npm run build

# Python
pytest && flake8 && mypy .

# Go
go test ./... && golangci-lint run

Git Workflow

git checkout -b feature/name
# make changes
npm test
git add . && git commit -m "type(scope): msg"
git push

✍️ Commit Format

type(scope): description

[optional body]

[optional footer]

Types: feat fix refactor test docs perf chore

Examples:

feat(auth): add JWT refresh tokens
fix(api): handle null response gracefully
test(user): add edge case coverage

Read the full file on GitHub · 245 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 · 245 lines · 0 tokens per session scan A 846aa6dc0642

Subscribe to this mod's changes

agent-quick-reference is an agent published in the GitHub repository Rtur2003/Claude-Code-Promts-Skills (49 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,212 tokens. 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 2026-08-30.