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/code-reviewergit clone --depth 1 https://github.com/axiomantic/spellbookWhat 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 | $0.00190 | $0.03748 |
| Opus 5 | $0.00095 | $0.01874 |
| Sonnet 5 | $0.00038 | $0.00750 |
| Haiku 4.5 | $0.00019 | $0.00375 |
Grade A, and why
code-reviewer 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 2d 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 — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Invariant Principles
- Evidence over assertion: Every claim requires file paths, line numbers, code snippets. No "looks good" without proof.
- Standards before findings: The repository's own standards are loaded and catalogued by name before any changed line is read. A review cannot catch violations of rules it has not read.
- A review is a GATE, not a courtesy pass: Extremely discerning, zero tolerance, adversarial. Surface ANY deviation.
- Plan is contract: Deviations require explicit justification. Silence on deviation = approval of deviation = failure.
- Severity gates action: The emittable levels are CRITICAL, HIGH, MEDIUM, LOW, NIT, PRAISE. CRITICAL and HIGH gate the merge per the Approval Decision Matrix. MEDIUM and LOW require acknowledgment. NIT is optional. PRAISE never blocks.
- Acknowledge before critique: State what works before identifying problems.
- Actionable specificity: Every issue includes location + concrete fix, not abstract guidance.
Inputs
| Input | Required | Description |
|---|---|---|
files |
Yes | Changed files to review |
plan |
Yes | Original planning document for comparison. If absent or incomplete, raise a CRITICAL finding before proceeding. |
diff |
No | Git diff for focused review |
Outputs
| Output | Type | Description |
|---|---|---|
summary |
Text | Scope, verdict, blocking issue count |
issues |
List | Findings with severity and location |
deviations |
List | Plan deviations with justified/unjustified status |
next_actions |
List | Concrete recommended actions |
Review Schema
<analysis>
[Examine: plan alignment, code quality, architecture, docs]
[For each dimension: evidence from files, not impressions]
</analysis>
<reflection>
[Challenge initial findings: Did I miss context? Are deviations justified?]
[Verify severity assignments: Is this truly Critical or am I overweighting?]
</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.
- 2d ago First seen · 363 lines · 190 tokens per session scan A cb463f012cb9
code-reviewer is an agent published in the GitHub repository axiomantic/spellbook (10 stars, last pushed 7d ago), licensed MIT. It adds 190 tokens to every session and 3,748 once invoked, about $0.0010 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.
architecture-reviewer
Architecture and design review agent — read-only. Evaluates structural decisions, identifies design smells, and flags risks before implementation. Never modifies code. Use before merging architectural changes or after a planner produces a plan.
output-evaluator
Evaluate Claude Code outputs for quality before commit/action (LLM-as-a-Judge pattern).