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/tirth8205/code-review-graph/review-changesnpx skills add tirth8205/code-review-graph --skill review-changesgit clone --depth 1 https://github.com/tirth8205/code-review-graphWhat 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 | $0.00014 | $0.00264 |
| Opus 5 | $0.00007 | $0.00132 |
| Sonnet 5 | $0.00003 | $0.00053 |
| Haiku 4.5 | $0.00001 | $0.00026 |
Grade A, and why
review-changes 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 2d 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.
What it actually says
Review Changes
Perform a thorough, risk-aware code review using the knowledge graph.
Steps
- Run
detect_changes_toolto get risk-scored change analysis. - Run
get_affected_flows_toolto find impacted execution paths. - For each high-risk function, run
query_graph_toolwith pattern="tests_for" to check test coverage. - Run
get_impact_radius_toolto understand the blast radius. - For any untested changes, suggest specific test cases.
Output Format
Provide findings grouped by risk level (high/medium/low) with:
- What changed and why it matters
- Test coverage status
- Suggested improvements
- Overall merge recommendation
Token Efficiency Rules
- Start with
get_minimal_context_tool(task="<your task>")before other graph tools. - Use
detail_level="minimal"on all calls. Only escalate to "standard" when minimal is insufficient. - Target: complete any review/debug/refactor task in ≤5 tool calls and ≤800 total output tokens.
- Read the implementation and its tests before changing code. The graph narrows scope; it does not replace the source.
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.
- 2d ago First seen · 31 lines · 14 tokens per session scan A 05a8a4b3e928
review-changes is a skill published in the GitHub repository tirth8205/code-review-graph (31,071 stars, last pushed 5d ago), licensed MIT. It adds 14 tokens to every session and 264 once invoked, about $0.0001 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 skills, from other repositories
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
office-hours
YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Saves a design doc. Use when asked to…
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
echo
Use when the user references past sessions, asks 'what did we do', 'do you remember', 'last session', 'recall', or 'continue from'.