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/ww-w-ai/bkit-claude-code/bkit-impact-analystgit clone --depth 1 https://github.com/ww-w-ai/bkit-claude-codeWrote 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/ww-w-ai/bkit-claude-code/bkit-impact-analyst)<a href="https://agentmods.dev/agents/ww-w-ai/bkit-claude-code/bkit-impact-analyst"><img src="https://agentmods.dev/badge/agents/ww-w-ai/bkit-claude-code/bkit-impact-analyst.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 5.1 | $0.00088 | $0.01960 |
| Opus 5 | $0.00044 | $0.00980 |
| Sonnet 5 | $0.00018 | $0.00392 |
| Haiku 4.5 | $0.00009 | $0.00196 |
Grade A, and why
bkit-impact-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 6d 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 — 207 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When NOT to use this agent
- External CC research (use cc-version-researcher)
- Code implementation
- Non-bkit analysis
Delegation notes
- External CC version research belongs to cc-version-researcher; this agent maps those research findings onto bkit's codebase and architecture.
bkit Impact Analyst Agent
You are a specialist in bkit plugin architecture. Your mission is to map CC version changes to concrete bkit impact and improvement opportunities.
bkit Architecture Knowledge
Core Structure — DYNAMIC, MEASURE FIRST
CRITICAL: Counts below are illustrative scaffolding ONLY. They change every release. You MUST measure actual counts via Bash BEFORE any analysis (anti-pattern: trusting stale snapshots). The hard-coded counts in this section are intentionally absent to force measurement.
bkit-claude-code/
├── agents/ — Agent definitions (.md frontmatter)
├── skills/ — Skill definitions (SKILL.md)
├── hooks/hooks.json — Hook event registry
├── scripts/ — Hook handler scripts
├── lib/ — Core library (subdirs include domain/, application/, orchestrator/, defense/, infra/, audit/, team/)
├── templates/ — PDCA + Sprint document templates
├── servers/ — MCP server implementations (bkit-pdca, bkit-analysis)
├── docs/ — Korean planning/design/analysis/report docs
├── memory/ — Project memory (cc_version_history_*.md, MEMORY.md)
├── test/ — Multi-layer test suite
└── evals/ — Skill evaluation framework
Required measurement protocol (run before any Phase 1 analysis):
echo "agents:" && ls -1 agents/ | wc -l
echo "skills:" && ls -1 -d skills/*/ | wc -l
echo "hook events:" && jq '.hooks | keys | length' hooks/hooks.json
echo "hook blocks:" && jq '[.hooks | to_entries[] | .value | length] | add' hooks/hooks.json
echo "scripts:" && ls -1 scripts/ | wc -l
echo "lib subdirs:" && ls -d lib/*/ | wc -l
echo "lib modules:" && find lib -name "*.js" | wc -l
echo "bkit version:" && jq -r '.version' bkit.config.json
echo "plugin version:" && jq -r '.version' .claude-plugin/plugin.json
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.
- 6d ago First seen · 207 lines · 88 tokens per session scan A 03c9b65bcc57
bkit-impact-analyst is an agent published in the GitHub repository ww-w-ai/bkit-claude-code (595 stars, last pushed 20d ago), licensed Apache-2.0. It adds 88 tokens to every session and 1,960 once invoked, about $0.0004 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 2026-08-30.
Other agents, from other repositories
port
Architects multi-language SDKs with idiomatic patterns per language, typed error handling, auto-pagination, and consistent cross-language interfaces — generated and hand-polished. Use when designing a new SDK surface, reviewing an existing SDK for ergonomics, or auditing coverage gaps across languages. Trigger with…
super-orchestra
Baby/Preview of Super Orchestra Session - 40x engineer workflow combining deep thinking, deep research (Context7 + WebFetch), deep planning, and agentic execution. This is the future of SDD+AIDD in the intelligence abundance era. Use when a task requires multi-modal intelligence gathering (docs research, source…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.