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/SyloRei/claude-godmodeWrote 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/sylorei/claude-godmode/pr-describe)<a href="https://agentmods.dev/commands/sylorei/claude-godmode/pr-describe"><img src="https://agentmods.dev/badge/commands/sylorei/claude-godmode/pr-describe/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/sylorei/claude-godmode/pr-describe"><img src="https://agentmods.dev/badge/commands/sylorei/claude-godmode/pr-describe.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 | $0.00037 | $0.00595 |
| Opus 5 | $0.00018 | $0.00298 |
| Sonnet 5 | $0.00007 | $0.00119 |
| Haiku 4.5 | $0.00004 | $0.00060 |
Grade A, and why
pr-describe scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pr-describe — draft a pull-request description
Compose a clear PR description from the branch's commits and diff against
its base branch. A reactive helper — it does not spawn agents and is not part
of the spine. (Pushing and opening the PR is /ship's job; this only drafts the
body.)
The Job
- Resolve the base branch and the commit range.
- Read the commits and the diff.
- Draft summary / what changed / test plan.
1. Resolve base and range
Determine the base branch (the branch this one will merge into) and the range of commits unique to the current branch:
BASE=$(git symbolic-ref --quiet refs/remotes/origin/HEAD 2>/dev/null | sed 's@.*/@@')
BASE=${BASE:-main}
git log --oneline "$BASE"..HEAD # commits on this branch
git diff --stat "$BASE"...HEAD # files changed vs base
If the base cannot be resolved, ask the user which branch this PR targets.
2. Draft the description
Build the body from the commit subjects/bodies and the diff — the commits tell you why, the diff tells you what:
## Summary
One or two sentences: what this PR does and why it exists.
## What changed
- Bullet per logical change, grounded in the commits and diff.
## Test plan
- How the change was verified (gates run, tests added, manual steps).
Keep it terse and factual. Do not invent test steps that were not run — if you cannot tell how it was tested, say so and ask. Print the description for the user to paste when opening the PR.
Output
Close the run with a short status block:
- Status — PR description drafted from the branch's commits and diff against the base.
- Produced — the Summary / What changed / Test plan body above, grounded in the commits and diff.
- Next — paste it into the PR when you open it;
/shipowns the actual push and PR creation.
Related
- /ship — owns pushing the branch and opening the PR; this command only drafts the body for it to carry.
- /changelog — draft a Keep a Changelog entry from the same commit range to accompany the PR.
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 · 80 lines · 37 tokens per session scan A 2ce5208f2461
pr-describe is a command published in the GitHub repository SyloRei/claude-godmode (3 stars, last pushed 3mo ago), licensed MIT. It adds 37 tokens to every session and 595 once invoked, about $0.0002 per session on Opus 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 2026-08-31.
Other commands, from other repositories
ccc-fork
Fork the current session for parallel exploration -- try multiple approaches, merge the best.
ccc-multi-repo
Orchestrate code changes across multiple repositories simultaneously using --add-dir.
ccc-parallel
Launch multiple Claude Code agents in parallel git worktrees for concurrent development.
ccc-ao
Composio AO — spawn parallel agents with worktree isolation.
ship
Branch, commit, open PR, gather Claude + every enabled AI reviewer (Copilot, CodeRabbit, etc.), fix/justify/resolve every finding, loop until clean, then merge. Run only when implementation is finished AND the owner has said to ship (e.g. "ship it") — never self-invoke just because the work looks done. To design and…
commit
Splits the current changes into atomic commits through ac:git-master, matching the repo's own commit style, with an optional typecheck plus test plus lint preflight and a push when an upstream exists. Accepts --skip-preflight and --no-push.