Forge is a command-line development environment that uses AI models as a pair programmer for working with code and shell commands. Developers use it to understand projects and carry out coding tasks through interactive, one-shot, or ZSH-based workflows. The catalogue entries extend Forge with reusable skills, agents, commands, and instructions.
Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/tailcallhq/forgecodenpx agentmods add skills/tailcallhq/forgecode/debug-cliWrote 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/tailcallhq/forgecode/debug-cli)<a href="https://agentmods.dev/skills/tailcallhq/forgecode/debug-cli"><img src="https://agentmods.dev/badge/skills/tailcallhq/forgecode/debug-cli/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/tailcallhq/forgecode/debug-cli"><img src="https://agentmods.dev/badge/skills/tailcallhq/forgecode/debug-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00049 | $0.01621 |
| Opus 5.5 | $0.00020 | $0.00648 |
| Sonnet 5.5 | $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 1mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- debug-cli — 100% identical, 0 lines differ
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.
- 1mo ago First seen · 212 lines · 49 tokens per session scan A 5a67fb126d8c
debug-cli is a skill published in the GitHub repository tailcallhq/forgecode (7,638 stars, last pushed today), licensed Apache-2.0. It adds 49 tokens to every session and 1,621 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
agent-observability
Instrument AI agents with tracing, token metrics, latency, and cost visibility. Use for reliability and debugging.
accesslint-audit
Find and fix WCAG 2.2 accessibility issues. Two modes — report (sweep a codebase or page, produce a prioritized written report, no edits) and fix (audit→edit→verify loop on a target). Prefers direct-CDP live-DOM auditing; falls back to a browser-MCP composition or HTML-string audits.
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
agent-qa-debug-fix
Debug, patch, and verify failed Agent QA runs from MCP evidence, artifacts, logs, and local code without hiding product or infrastructure defects.
api-analyzer
Validates whether an API request is correct based on provided inputs (method, URL, headers, body, auth, query params).
accesslint-scan
Audit a live page for accessibility issues, locate each WCAG violation precisely, and return a selector-grounded fix worklist without editing.