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 agents/axiomantic/spellbook/pr-creatorgit 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.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 | $0.00075 | $0.01421 |
| Opus 5 | $0.00037 | $0.00711 |
| Sonnet 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 3d 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.
- 3d 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 $0.0004 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 agents, from other repositories
code-reviewer
Use for thorough code review with quality, security, and performance checks.
integration-reviewer
Runtime integration validator — read-only. Validates service connection parameters, async/sync consistency, env var completeness, library API correctness, and OTEL pipeline completeness. Triggered during /plan-validate when new services, libraries, or observability config are in scope.
plan-challenger
Adversarial plan review agent — read-only. Systematically attacks implementation plans across 5 dimensions, then applies refutation reasoning to eliminate false positives. Never modifies code. Use before committing to any significant implementation plan.
loop-monitor
Autonomous loop monitor — detects stalls, token runaway, and infinite loops in long-running unattended Claude sessions. Use alongside a watchdog process when running autonomous pipelines.
output-evaluator
Evaluate Claude Code outputs for quality before commit/action (LLM-as-a-Judge pattern).
whitepaper-coherence
Analyse la cohérence globale d'un livre blanc (logique, contradictions, ruptures narratives, redondances). Utiliser pour auditer un whitepaper avant publication.