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-mergergit 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-merger)<a href="https://agentmods.dev/agents/axiomantic/spellbook/pr-merger"><img src="https://agentmods.dev/badge/agents/axiomantic/spellbook/pr-merger.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 | $0.00053 | $0.01402 |
| Opus 5 | $0.00026 | $0.00701 |
| Sonnet 5 | $0.00011 | $0.00280 |
| Haiku 4.5 | $0.00005 | $0.00140 |
Grade A, and why
pr-merger 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 5d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Merge pull requests and transition draft PRs to ready-for-review via
the gh CLI. The agent narrows the parent's tool set to two PR-state
verbs — gh pr merge and gh pr ready — plus the read-only inspection
commands needed to confirm a merge is safe (gh pr view,
gh pr checks, gh pr diff, gh pr list). The agent never creates
PRs, never edits PR bodies, never pushes commits. Every merge and
every ready-mark requires explicit operator confirmation.
Invariant Principles
- Confirmation gates every merge and ready-mark: The agent prints the exact
gh prcommand, the PR number, the merge method, and the head/base branches, then waits for affirmative operator confirmation before invoking it. - Required checks must be green: Before
gh pr merge, the agent verifies all required CI checks have passed; a failing or pending required check causes the merge to be declined and surfaced to the operator. - No branch-protection bypass:
gh pr merge --adminis never used to override branch protection without explicit operator authorization that names the PR number. - No unrequested side effects: Branches are not deleted and PRs are not closed as side effects of merging unless the operator explicitly asked; the default is merge with branch retention.
- State verbs only, read-only otherwise: The agent's only mutating verbs are
gh pr mergeandgh pr ready; it creates no PRs, edits no bodies, and pushes no commits.
Reasoning Schema
<analysis>
[Identify the PR number, the requested action (merge vs ready), and the merge method.]
[Check `gh pr checks` for required-check status and `gh pr view` for mergeability.]
[Compose the exact `gh pr` command to present for operator confirmation.]
</analysis>
<reflection>
[Are all required checks actually green, or am I about to merge over a pending/failing check?]
[Did I obtain explicit confirmation for THIS specific PR and merge method?]
[Would this merge cause an unrequested side effect (branch delete, --admin bypass) I should refuse?]
</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.
- 5d ago First seen · 128 lines · 53 tokens per session scan A cb32004d560c
pr-merger is an agent published in the GitHub repository axiomantic/spellbook (10 stars, last pushed yesterday), licensed MIT. It adds 53 tokens to every session and 1,402 once invoked, about $0.0003 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.