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 skills/oleg494/coding-kit/code-graph-reviewnpx skills add oleg494/coding-kit --skill code-graph-reviewgit clone --depth 1 https://github.com/oleg494/coding-kitWhat 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 | $0.00071 | $0.00618 |
| Opus 5 | $0.00036 | $0.00309 |
| Sonnet 5 | $0.00014 | $0.00124 |
| Haiku 4.5 | $0.00007 | $0.00062 |
Grade A, and why
code-graph-review 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 yesterday.
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.
What it actually says
Code graph review: what will the change break
The code-review-graph MCP server answers "what will this N-file change break" — impact/blast radius over the DIFF, dead-code, communities, flows.
Workflow (order of application)
- Changes ready → diagnose first (lsp): 0 errors before any linter.
- Rebuild the graph —
build_or_update_graph_tool(incrementally). A stale graph = false analysis. - Run
detect_changes— diff → risk score, priorities (what to look at first), test gaps. This is the main review tool. - Assess blast radius —
get_impact_radius(BFS depth over the diff),get_review_context(code snippets). Ask: "what will the N-file change break". - Check affected flows —
get_affected_flows/list_flows: which user paths pass through the changed files. - Architecture (if needed) —
get_hub_nodes(who is a hub),get_bridge_nodes(bridges),get_surprising_connections,get_architecture_overview,get_knowledge_gaps. - Dead code / rename —
refactor_tool(mode="dead_code");refactor_tool(mode="rename")→apply_refactor_tool. - Verify dead-code false positives via lsp (
find_references), don't delete blindly.
Table: task → tool
| Task | Tool |
|---|---|
| change review (diff → risk → priorities) | detect_changes |
| blast radius of an N-file change | get_impact_radius, get_review_context |
| affected execution paths | get_affected_flows, list_flows |
| dead code | refactor_tool(mode="dead_code") |
| hubs/bridges/unexpected coupling | get_hub_nodes, get_bridge_nodes, get_surprising_connections |
| weak spots | get_knowledge_gaps, get_suggested_questions |
| rename with preview | refactor_tool(mode="rename") → apply_refactor_tool |
Pitfalls
- dead-code produces false positives on callback patterns and
Thread(target=...)— verify via lsp, don't delete blindly. - The graph builds/updates incrementally:
build_or_update_graph_toolafter changes — otherwise the data is stale.
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.
- yesterday First seen · 37 lines · 71 tokens per session scan A 7520d44f02d7
code-graph-review is a skill published in the GitHub repository oleg494/coding-kit (1 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 618 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
run
Execute a named agent role with optimized instructions. Explicit invocation only ($run). Never trigger implicitly.
tip
Deliver a transformative life perspective shift and a productivity tip. Use when the user invokes /tip or wants non-technical inspiration or a fresh mental model.
agentic-security-review
Run a security and dependency audit for agent systems, tool-using AI apps, MCP/A2A integrations, or security-sensitive AI-generated code. Check slopsquatting risk, tool shadowing, rug pulls, memory/context poisoning, secrets, unsafe permissions, and common CWE patterns. Use when asked for security review, dependency…
agentic-spec
Create a structured specification before agentic coding work. Assemble the six context types, scale rigor for prototype/internal/production tasks, produce SPEC.md, and configure focused AGENTS.md boundaries. Use when asked to write a spec, plan a feature, design an agent/system, define architecture, or create…
agentic-evals
Design evaluation contracts and test plans for agentic systems. Create deterministic tests, trajectory evals, quality dimensions, gold-set criteria, and CI gates before or after implementation. Use when asked for tests first, an eval plan, success criteria, non-deterministic testing, LLM-as-judge setup, or…
agentic-production-readiness
Prepare an AI agent system for production operation. Cover SHIELD controls, sandbox/canary/production rollout, OpenTelemetry observability with GenAI semantic conventions, Agent Card drafting, governance, and post-deploy monitoring. Use for production readiness checks, go-live checklists, agent monitoring, agent…