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 agentmods add skills/justrach/codegraff2/debug-clinpx skills add justrach/codegraff2 --skill debug-cligit clone --depth 1 https://github.com/justrach/codegraff2What 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 | $0.00049 | $0.01621 |
| Opus 5 | $0.00024 | $0.00811 |
| Sonnet 5 | $0.00010 | $0.00324 |
| Haiku 4.5 | $0.00005 | $0.00162 |
Grade A, and why
debug-cli 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 yesterday.
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.
This is a copy
100% identical to debug-cli — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI Debug Skill
This skill provides a systematic workflow for debugging and verifying changes to the forge CLI application.
Core Principles
- Always get latest docs first: Run
--helpto see current commands and options - Use
-pfor testing: Test forge by giving it tasks with the-pflag - Never commit: This is for debugging only - don't commit changes
- Clone conversations: When debugging conversation bugs, clone the source conversation before reproducing
Workflow
1. Build the Application
Always build in debug mode after making changes:
cargo build
Never use cargo build --release for debugging - it's significantly slower and unnecessary for verification.
2. Get Latest Documentation
Always start by checking the latest help to understand current commands and options:
# Main help - do this first
./target/debug/forge --help
# Command-specific help
./target/debug/forge [COMMAND] --help
# Subcommand help
./target/debug/forge [COMMAND] [SUBCOMMAND] --help
3. Test with -p Flag
Use the -p flag to give forge a task to complete without interactive mode:
# Test with a simple prompt
./target/debug/forge -p "create a hello world rust program"
# Test with specific functionality
./target/debug/forge -p "read the README.md file and summarize it"
# Test with complex tasks
./target/debug/forge -p "analyze the code structure and suggest improvements"
4. Debug with Conversation Dumps
When debugging prompts or conversation issues, use conversation dump to export conversations. The command automatically creates a timestamped file:
# Dump conversation as JSON (creates: YYYY-MM-DD_HH-MM-SS-dump.json)
./target/debug/forge conversation dump <conversation-id>
# Export as HTML for human-readable format (creates: YYYY-MM-DD_HH-MM-SS-dump.html)
./target/debug/forge conversation dump --html <conversation-id>
# Use dumped JSON to reproduce issues
./target/debug/forge --conversation 2025-11-23_12-28-52-dump.json
What ships with it
2 files 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.
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.
- yesterday First seen · 212 lines · 49 tokens per session scan A 5a67fb126d8c
debug-cli is a skill published in the GitHub repository justrach/codegraff2 (24 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 1,621 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to debug-cli, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…