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 commands/pablomarin/claude-codex-forge/new-featuregit clone --depth 1 https://github.com/pablomarin/claude-codex-forgeWrote 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/commands/pablomarin/claude-codex-forge/new-feature)<a href="https://agentmods.dev/commands/pablomarin/claude-codex-forge/new-feature"><img src="https://agentmods.dev/badge/commands/pablomarin/claude-codex-forge/new-feature.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00000 | $0.19562 |
| Opus 5 | $0.00000 | $0.09781 |
| Sonnet 5 | $0.00000 | $0.03912 |
| Haiku 4.5 | $0.00000 | $0.01956 |
Grade B, and why
new-feature scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
[ -f .claude/playwright-dir ] && NODE_DIRS="$(cat .claude/playwright-dir) $NODE_DIRS" This is a copy
86% identical to fix-bug — 654 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 1,311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
New Feature Workflow
This workflow is MANDATORY. Follow every step in order. If any required command/skill fails with "Unknown skill", STOP and alert the user.
Required Plugins
This workflow requires the following plugins to be installed AND enabled:
| Plugin | Skills/Commands Used |
|---|---|
superpowers@claude-plugins-official |
/superpowers:brainstorming, /superpowers:writing-plans, /superpowers:subagent-driven-development (default executor), /superpowers:executing-plans (headless mode), /superpowers:systematic-debugging |
pr-review-toolkit@claude-plugins-official |
code-simplifier agent, code-reviewer agent, /pr-review-toolkit:review-pr |
To enable plugins, add to ~/.claude/settings.json:
{
"enabledPlugins": {
"superpowers@claude-plugins-official": true,
"pr-review-toolkit@claude-plugins-official": true,
"frontend-design@claude-plugins-official": true
}
}
Pre-Flight Checks
1. Create Isolated Workspace (MANDATORY)
Check if already in a worktree:
if [[ "$(pwd)" == *".worktrees/"* ]]; then
echo "STATE: ALREADY_IN_WORKTREE"
else
echo "STATE: NEEDS_WORKTREE"
fi
If ALREADY_IN_WORKTREE:
- You're already isolated — continue with current workspace
- Surface drift on the parent default branch (advisory; no auto-FF from inside a worktree)
# DRIFT-PREFLIGHT-ALREADY-BEGIN (byte-identical with commands/fix-bug.md — enforced by test-contracts.sh)
ROOT="$(git rev-parse --show-toplevel)"
LIB="$ROOT/.claude/hooks/lib/default-branch.sh"
[ ! -f "$LIB" ] && LIB="$ROOT/hooks/lib/default-branch.sh"
DEFAULT_BRANCH=$(bash "$LIB" 2>/dev/null) \
|| { DEFAULT_BRANCH="main"; echo " ⚠ default-branch helper bailed; assuming 'main' (drift check may be wrong on non-main repos)" >&2; }
ALREADY_FETCH_OK=true
git fetch origin --quiet 2>/dev/null || ALREADY_FETCH_OK=false
# Behind-check: only if FETCH succeeded AND both refs exist. Skipping on fetch failure
# prevents reporting drift against a stale origin/* ref. Also guards rev-list exit-128.
if [ "$ALREADY_FETCH_OK" = "true" ] \
&& git rev-parse --verify "$DEFAULT_BRANCH" >/dev/null 2>&1 \
&& git rev-parse --verify "origin/$DEFAULT_BRANCH" >/dev/null 2>&1; then
BEHIND=$(git rev-list --count "$DEFAULT_BRANCH..origin/$DEFAULT_BRANCH" 2>/dev/null || echo "")
if [[ "$BEHIND" =~ ^[0-9]+$ ]] && [ "$BEHIND" -gt 0 ]; then
echo " ⚠ Parent '$DEFAULT_BRANCH' is $BEHIND commits behind origin (skipping auto-FF from worktree)"
fi
fi
# DRIFT-PREFLIGHT-ALREADY-END
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.
- 4d ago First seen · 1,311 lines · 0 tokens per session scan B 391e239b2d99
new-feature is a command published in the GitHub repository pablomarin/claude-codex-forge (5 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 19,562 tokens. A static security scan graded it B with 1 finding (reads agent configuration directories). It is 86% identical to fix-bug, differing in 654 lines, and is treated as a copy.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.