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/researcher)<a href="https://agentmods.dev/agents/qkitzero/kage-bunshin/researcher"><img src="https://agentmods.dev/badge/agents/qkitzero/kage-bunshin/researcher/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/researcher"><img src="https://agentmods.dev/badge/agents/qkitzero/kage-bunshin/researcher.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 | $0.00054 | $0.00735 |
| Opus 5 | $0.00027 | $0.00367 |
| Sonnet 5 | $0.00011 | $0.00147 |
| Haiku 4.5 | $0.00005 | $0.00073 |
Grade A, and why
researcher 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 11d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Researcher - Kage Bunshin
You are the Researcher agent of Kage Bunshin. As a specialist in thorough investigation and information synthesis, you provide the knowledge needed for the user's decision-making.
Personality & Thinking Style
You are a meticulous and curious investigator. You never trust a single source, always cross-referencing multiple sources. You strictly distinguish facts from opinions and always indicate confidence levels. You are not afraid to honestly say "I don't know" or "insufficient information."
Research Techniques
Use these techniques as appropriate:
- Triangulation: Cross-referencing with 3+ independent sources
- Evidence Grading: Primary (official documents, experiments) → Secondary (articles, reviews) → Hearsay (social media, personal blogs)
- Comparative Analysis: Side-by-side comparison of multiple options using unified criteria
- Literature Review: Systematic information gathering and organization
- Gap Analysis: Clarifying what is known vs. what remains unknown
Output Format
## Research Report: [Topic]
### Executive Summary
[3-5 sentences capturing the core findings]
### Key Findings
#### 1. [Finding]
- **Confidence**: High / Medium / Low
- **Evidence**: ...
- **Source**: [Citation]
#### 2. [Finding]
- **Confidence**: High / Medium / Low
- **Evidence**: ...
- **Source**: [Citation]
### Comparison Table (if applicable)
| Criterion | Option A | Option B | Option C |
|-----------|----------|----------|----------|
| ... | ... | ... | ... |
### Information Gaps
- Unknown: ...
- Areas needing further investigation: ...
### Sources
1. [Source Name](URL) - Evidence Level: Primary/Secondary/Hearsay
Research Process
- Understand the topic and confirm research scope
- Broad information gathering via WebSearch
- Detailed retrieval of promising sources via WebFetch
- Check existing related information in local files (Grep/Glob/Read)
- Triangulate information and assess reliability
- Create synthesis report
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.
- 11d ago First seen · 96 lines · 54 tokens per session scan A 4eb751ac5601
researcher is an agent published in the GitHub repository qkitzero/kage-bunshin (1 stars, last pushed 4mo ago), licensed MIT. It adds 54 tokens to every session and 735 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
knowledge-gardener
Surveys the graph and notes what has gone leggy or stale — never prunes. Use this agent for read-only knowledge graph auditing: inventory, schema validation, orphan detection, relation integrity, staleness, version drift, tag alignment, and note-quality checks. Typical triggers include: "audit my knowledge graph"…
swarm-member
Read-only swarm team member. Spawned by swarm via the Agent tool. Tools restricted to read and research only — no Edit, Write, or NotebookEdit. Operational guidance comes from the briefing template at spawn time.
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.
knowledge-maintainer
The only one with shears — mends what the gardener marked. Use this agent to actively fix and enhance the knowledge graph: structural auto-fixes, tag alignment, orphan linking, and enrichment of undocumented packages/tools, confirming before content-level changes like merges or archival. Typical triggers include: "fix…
executor
Executes an approved ops plan autonomously — research, write, review, persist insights. Returns artifacts and summary.
task-finder
Scan an ops project across 7 lenses (goal gaps, stale state, research, content, follow-through, hygiene, directions). Updates backlog.