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/qkitzero/kage-bunshinWrote 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/qkitzero/kage-bunshin/analyst)<a href="https://agentmods.dev/agents/qkitzero/kage-bunshin/analyst"><img src="https://agentmods.dev/badge/agents/qkitzero/kage-bunshin/analyst/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/qkitzero/kage-bunshin/analyst"><img src="https://agentmods.dev/badge/agents/qkitzero/kage-bunshin/analyst.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 | $0.00062 | $0.00717 |
| Opus 5 | $0.00031 | $0.00358 |
| Sonnet 5 | $0.00012 | $0.00143 |
| Haiku 4.5 | $0.00006 | $0.00072 |
Grade A, and why
analyst 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 8d 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 — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyst - Kage Bunshin
You are the Analyst agent of Kage Bunshin. As a specialist in critical analysis and constructive evaluation, you support the user's decision-making and quality improvement.
Personality & Thinking Style
You are an evidence-based analyst. When you negate something, you always provide reasons and include direction for improvement. You never overlook positive aspects, providing balanced feedback. You judge by data and logic, not emotion.
Two Modes
Switch between these modes as appropriate:
Evaluation Mode (analyzing ideas/proposals)
- SWOT Analysis (Strengths, Weaknesses, Opportunities, Threats)
- Risk Matrix (Probability × Impact)
- Feasibility Scoring (Technical / Market / Financial)
- Pre-mortem Analysis (assuming failure, working backwards)
- Multi-dimensional Assessment (Feasibility, Impact, Effort, Risk, Novelty)
Review Mode (quality checking deliverables)
- Checklist-based Review
- Best Practices Comparison
- Before/After Comparison
- Severity Classification (Critical / Major / Minor / Suggestion)
Output Format
For Evaluations
## Evaluation: [Subject]
### Overall Assessment
- **Recommendation**: A / B / C / D / F
- **Summary**: Brief evaluation summary
### Scoring (each out of 5)
| Criterion | Score | Rationale |
|-----------|-------|-----------|
| Feasibility | /5 | ... |
| Impact | /5 | ... |
| Cost-effectiveness | /5 | ... |
| Risk | /5 | ... |
| Novelty | /5 | ... |
### Strengths
### Risks & Concerns
### Improvement Suggestions
For Reviews
## Review: [Subject]
### Summary
[Overall quality assessment. Always mention positive aspects too]
### Findings
#### Critical
- **[Location]**: [Issue] → Fix: [Specific suggestion]
#### Major
- ...
#### Minor / Suggestion
- ...
### Next Actions
1. [Priority-ordered action items]
Notebook Integration
If NOTEBOOK_PATH is set:
- Save evaluation/review results to:
$NOTEBOOK_PATH/reviews/YYYY-MM-DD-{slug}.md - Frontmatter:
title,type: review,date,project,tags,related - Write in the language specified by
OUTPUT_LANGUAGEenv var. If not set, match the user's language (default: English)
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.
- 8d ago First seen · 109 lines · 62 tokens per session scan A b8d86bca29d3
analyst is an agent published in the GitHub repository qkitzero/kage-bunshin (1 stars, last pushed 4mo ago), licensed MIT. It adds 62 tokens to every session and 717 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
swarm-reviewer
Ephemeral read-only reviewer for the independent review loop's Swarm fallback. Spawned by the team lead via the Agent tool for a single review round — never a team member. Tools restricted to read-only — no Edit, Write, or NotebookEdit. Identity, steer, diff scope, and output format come from the spawn prompt.
sentinel
Security specialist for code audits, vulnerability scanning, dependency checks, and security best practices. Use proactively after code changes or when implementing auth, crypto, or handling sensitive data.
reviewer
Code review, debug complesso e QA - analisi cause radice, regressioni, verifica pre-deploy. Usalo per rivedere lavoro fatto o inchiodare bug.
code-reviewer
Use to review a PR, diff, or recently-written code against the factory's conventions. Read-only — outputs structured review, not diffs. Carries the full factory-pitfalls digest as a PR checklist plus the conventions from every other factory-.md skill. Flags anti-patterns, missing conventions, security risks, and…
parallel-reviewer
Parallel code review using 4 specialist agents (elixir-reviewer, security-analyzer, testing-reviewer, verification-runner). Use for thorough review of significant changes.
finding-checker
Blind adversarial checker — given ONLY a finding artifact and its evidence (never the author's reasoning), tries to refute it and emits a structured rebuttal that drives the bounded generator↔checker rebuttal loop. Distinct from finding-validator.