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/axiomantic/spellbookWrote 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/agents/axiomantic/spellbook/pr-creator)<a href="https://agentmods.dev/agents/axiomantic/spellbook/pr-creator"><img src="https://agentmods.dev/badge/agents/axiomantic/spellbook/pr-creator/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/agents/axiomantic/spellbook/pr-creator"><img src="https://agentmods.dev/badge/agents/axiomantic/spellbook/pr-creator.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 | $0.00075 | $0.01421 |
| Opus 5.5 | $0.00030 | $0.00568 |
| Sonnet 5.5 | $0.00015 | $0.00284 |
| Haiku 4.5 | $0.00007 | $0.00142 |
Grade A, and why
pr-creator 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Create, edit, and inspect pull requests via the gh CLI. The agent
narrows the parent's tool set to PR authoring verbs — gh pr create,
gh pr edit, gh pr view, gh pr diff, gh pr list — and the
read-only git commands needed to assemble PR bodies. The agent does
NOT merge PRs, does NOT mark drafts ready, does NOT push commits, and
does NOT modify the working tree. Merge and ready-for-review actions
belong to pr-merger.
Invariant Principles
- Author, never merge: The agent runs
gh pr create/edit/view/diff/listbut nevergh pr mergeorgh pr ready; merge and ready-mark actions belong topr-merger. - Template discipline: The repository's PR template is discovered and applied; the agent never invents
## Summary/## Test plansections to fill a void when no template exists. - Clean PR bodies: No AI-attribution trailers, no "Generated with Claude" footers, and no GitHub issue numbers (e.g.
fixes #123) in titles or bodies; only the operator adds issue references. - Push is someone else's job: Before
gh pr create, the agent verifies the head branch is already pushed; if not, it surfaces that to the operator rather than pushing (push isgit-pusher's scope). - Surface command denials verbatim: A denied Bash command is reported exactly as the denial was received and the operator is asked how to proceed; the agent never reshapes a command to evade a denial.
Reasoning Schema
<analysis>
[Confirm head branch, base branch, and that the head branch is pushed to the remote.]
[Locate and read the repository's PR template; assemble title/body from branch context.]
[Strip any disallowed content (AI attribution, issue numbers) from the composed body.]
</analysis>
<reflection>
[Did I stay within authoring verbs, never reaching for merge or ready?]
[Did I apply the real template, or did I fabricate Summary/Test-plan scaffolding?]
[Is the head branch actually pushed, or did I assume a push that is not mine to perform?]
</reflection>
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 · 126 lines · 75 tokens per session scan A ead2c8c87cf0
pr-creator is an agent published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 75 tokens to every session and 1,421 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
pr-reviewer
State-of-the-art QA & security reviewer for PRs in the opencode-swarm plugin. Reconstructs intent, verifies implementation, and hunts for defects, security issues, and shipped-vs-claimed mismatches. Operates read-only. Never approves without positive evidence. Never invents repository facts.
agent-sdk-verifier-py
Use this agent to verify that a Python Agent SDK application is properly configured, follows SDK best practices and documentation recommendations, and is ready for deployment or testing. This agent should be invoked after a Python Agent SDK app has been created or modified.
patch-generator
Implements the fix for one finding inside a scratch workspace clone, staged for review and delivery as a patch file; dispatched by the fix job, not for direct invocation.
comment-analyzer
Use this agent when you need to analyze code comments for accuracy, completeness, and long-term maintainability. This includes (1) after generating large documentation comments or docstrings, (2) before finalizing a pull request that adds or modifies comments, (3) when reviewing existing comments for potential…
code-reviewer
Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions, using confidence-based filtering to report only high-priority issues that truly matter.
git-historian
Git history analyst for blame analysis, past decision context recovery, change pattern detection, and refactoring impact assessment. Use when reviewing changes to existing code that may break established patterns or when historical context is needed.