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 skills add qkitzero/kage-bunshin --skill evaluategit 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/skills/qkitzero/kage-bunshin/evaluate)<a href="https://agentmods.dev/skills/qkitzero/kage-bunshin/evaluate"><img src="https://agentmods.dev/badge/skills/qkitzero/kage-bunshin/evaluate/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/skills/qkitzero/kage-bunshin/evaluate"><img src="https://agentmods.dev/badge/skills/qkitzero/kage-bunshin/evaluate.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 | $0.00050 | $0.00780 |
| Opus 5.5 | $0.00020 | $0.00312 |
| Sonnet 5.5 | $0.00010 | $0.00156 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
evaluate 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 1mo 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evaluate Skill
A workflow that creates an Agent Team of Researcher and Analyst to perform multi-dimensional evaluation through iterative investigation and assessment.
Workflow
Step 1: Understand the Evaluation Target
Accurately understand the idea, proposal, or plan presented by the user. Clarify:
- Overview of the evaluation target
- Context (market, organization, technical environment, etc.)
- Any priority evaluation axes if specified
Step 2: Retrieve Past Notebook Context
If NOTEBOOK_PATH is set, search for past entries related to the evaluation target:
- Grep
$NOTEBOOK_PATH/reviews/and$NOTEBOOK_PATH/research/for keywords from the target - Read up to 3 matching entries (frontmatter + first 200 characters of body)
- Include the retrieved content as context when creating the team
Skip this step if zero matches or NOTEBOOK_PATH is not set.
Step 3: Create Agent Team
Create a team with the following teammates using their agent definitions from .claude/agents/:
Teammates:
researcher— gathers background information and evidenceanalyst— performs structured evaluation and scoring
Team instructions:
Evaluation target: [Description]
[Past Notebook context if found]
Collaboration protocol:
1. Researcher investigates: similar cases, market/tech landscape, competitors, risks, required resources
2. Analyst performs initial evaluation based on research (6 dimensions: Feasibility, Market Fit, Effort, Risk, Innovation, Impact)
3. Analyst identifies information gaps and requests additional research from Researcher
4. Researcher conducts targeted follow-up investigation
5. Analyst refines scores and produces final Go / Conditional Go / No-Go recommendation
6. Continue iterating until Analyst is confident in the assessment (aim for 2-3 rounds)
Rules:
- Output language: Use the language specified by OUTPUT_LANGUAGE env var. If not set, match the user's language (default: English)
- If NOTEBOOK_PATH is set: Researcher saves to $NOTEBOOK_PATH/research/, Analyst saves to $NOTEBOOK_PATH/reviews/
- Each agent writes its own deliverables with structured frontmatter
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.
- 1mo ago First seen · 100 lines · 50 tokens per session scan A 728bd7f76347
evaluate is a skill published in the GitHub repository qkitzero/kage-bunshin (0 stars, last pushed 6mo ago), licensed MIT. It adds 50 tokens to every session and 780 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
scaffold
Set up or align a non-code ops/PM repo with the ops folder structure, CLAUDE.md, and INDEX.md hierarchy.
find-opps
Find new directions for an ops project — adjacent opportunities, strategic gaps, preparatory research. Use when known work is well-mined and you need to look outward.
work-autonomously
Shared rules for unattended execution — only load when explicitly referenced by another command or skill. Never auto-trigger based on user prompts.
factory-db-migration
The operational discipline for running a destructive change against a production database — schema migrations, data backfills, one-shot RPCs, historical seed imports. Adjacent to factory-data-layer.md (schema design) and factory-deployment.md (where migrations execute in CI) — this skill is about the runbook around…
factory-api
API conventions for both server actions and tRPC builds. Covers the decision between them, per-mutation Zod input schemas, central router composition, pagination shape, multi-field search via Drizzle ilike + or(), mutation lifecycle hooks, conditional query enabling, stale-time defaults, error response shape and…
factory-ci
CI and pull-request review conventions. One canonical .github/workflows/ci.yml is the merge gate (typecheck, lint, test, build, claude-review); branch protection's required-checks list matches the job list 1:1; anthropics/claude-code-action@v1 reviews every PR against the factory-pitfalls.md checklist as a required…