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.
git clone --depth 1 https://github.com/ddgonzal3/rallyWrote 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/ddgonzal3/rally/rally-park)<a href="https://agentmods.dev/commands/ddgonzal3/rally/rally-park"><img src="https://agentmods.dev/badge/commands/ddgonzal3/rally/rally-park/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/commands/ddgonzal3/rally/rally-park"><img src="https://agentmods.dev/badge/commands/ddgonzal3/rally/rally-park.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.01366 |
| Opus 5 | $0.00000 | $0.00683 |
| Sonnet 5 | $0.00000 | $0.00273 |
| Haiku 4.5 | $0.00000 | $0.00137 |
Grade A, and why
rally-park scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
STATUS=$(curl -s -o /tmp/rally-park-resp -w "%{http_code}" \ How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Park: Stash current Claude thread
You are parking the current thread so its tree slot frees up. Branch + Claude convo persist on remote + in Rally's DB. Resume later from any tree.
When to use
User invokes /rally-park or says any of: "park this", "park it", "set this aside", "stash this for later", "I'll come back to this", "save and switch."
Steps
1. Verify in a git repo
git rev-parse --show-toplevel
If error, abort and tell user: "rally-park needs to run inside a git repo."
2. Refuse to park main/master
BRANCH=$(git branch --show-current)
If $BRANCH is main or master, abort: "Refusing to park main/master. Make a feature branch first."
3. Commit WIP
Stage everything, commit with auto-message. Skip if nothing to commit. Use --no-verify — parking should never fail on hooks.
git add -A
if ! git diff --cached --quiet; then
git commit -m "park: WIP" --no-verify
fi
4. Auto-name branch if still placeholder
If $BRANCH matches ^danny/[1-8]$, generate a slug from THIS conversation's actual work. Pick 2–4 lowercase words separated by -, describing what was being worked on. Examples: fix-audition-crash, mood-classifier-tuning, slots-rail-impl.
Must be [a-z0-9-]+ only. No spaces, no dots, no slashes beyond the danny/ prefix.
NEW_BRANCH="danny/<your-slug>"
git branch -m "$NEW_BRANCH"
BRANCH="$NEW_BRANCH"
If branch already has a meaningful name (not danny/N), keep it as-is.
5. Push to remote
git push -u origin "$BRANCH" --no-verify
6. Generate one-line summary
Write a short (≤80 chars) plain-text summary of what was being worked on. No quotes, no newlines.
7. Find current Claude session id
Claude Code stores per-session JSONL files at
~/.claude/projects/<encoded-cwd>/<session-id>.jsonl. The encoded cwd is the
absolute path with / replaced by - (the leading slash becomes a leading
dash). The newest file = the current session.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 164 lines · 0 tokens per session scan A 3b6438e24967
rally-park is a command published in the GitHub repository ddgonzal3/rally (6 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,366 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
commit
A command that examines staged Git changes and proposes a commit message using the Conventional Commits format, such as feat, fix, or docs. Git is a tool for tracking changes to code.
merge-conflict-analysis
You are analyzing merge conflicts for PR #${{ pr-number }}.
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.
doctor
Diagnosticar y reparar problemas del framework Don Cheli, git y entorno. Usa cuando el usuario dice "doctor", "problemas del framework", "don cheli no funciona", "repair Don Cheli", "debug setup", "setup broken", "framework broken", "reparar entorno". Detecta y repara issues de configuración, git y dependencias…
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
handoff
Export a Waybill Bundle by default, or import one when requested.