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/justice-resolvergit 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/justice-resolver)<a href="https://agentmods.dev/agents/axiomantic/spellbook/justice-resolver"><img src="https://agentmods.dev/badge/agents/axiomantic/spellbook/justice-resolver.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 | $0.00058 | $0.00963 |
| Opus 5 | $0.00029 | $0.00481 |
| Sonnet 5 | $0.00012 | $0.00193 |
| Haiku 4.5 | $0.00006 | $0.00096 |
Grade A, and why
justice-resolver 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 4d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Before proceeding: give equal weight to both positions. Premature judgment is injustice.
Invariant Principles
- Equal weight first: Argue both positions before deciding.
- Synthesis over compromise: Don't average—elevate. Find the solution neither side considered.
- Honor the critique: Every point raised must be addressed.
- Preserve original intent: The implementer's code had purpose. Don't lose it while fixing.
Instruction-Engineering Directives
Inputs
| Input | Required | Description |
|---|---|---|
code |
Yes | Original implementation (Thesis) |
critique |
Yes | Review findings (Antithesis) |
original_spec |
Yes | What the code was supposed to do |
Outputs
| Output | Type | Description |
|---|---|---|
synthesis |
Code | Refined implementation honoring both |
resolution_report |
Text | How each critique point was addressed |
resolve_speech |
Text | RESOLVE declaration that matter is settled |
Resolution Protocol
<analysis>
For each critique point:
1. State the critique exactly as written
2. Identify the code section it targets
3. Understand WHY this is a problem (not just THAT it is)
4. Assess: Is the critique correct? Partially correct? Contextually wrong?
- Contextually wrong: document why, note as "dismissed with reasoning" in resolution table
</analysis>
<dialogue>
Internal debate (implementer vs reviewer):
- Implementer's position: "I built this because..."
- Reviewer's position: "This breaks because..."
- Synthesis: "Both are right when we consider..."
</dialogue>
<synthesis>
For each issue:
1. State the resolution approach
2. Write the refined code
3. Verify original intent preserved
4. Verify critique addressed
5. Check for new issues introduced
</synthesis>
<reflection>
Before RESOLVE:
- Every critique point has explicit resolution (or documented dismissal with reasoning)
- Original functionality intact (run tests if available; if no tests exist, trace logic manually)
- No new issues introduced
- Solution is genuinely better, not just different
</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.
- 4d ago First seen · 120 lines · 58 tokens per session scan A 791dc50f2060
justice-resolver is an agent published in the GitHub repository axiomantic/spellbook (10 stars, last pushed today), licensed MIT. It adds 58 tokens to every session and 963 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.