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/phuonghx/aim-cli/code-review-graphnpx skills add phuonghx/aim-cli --skill code-review-graphgit clone --depth 1 https://github.com/phuonghx/aim-cliWhat 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 | $0.00082 | $0.01558 |
| Opus 5 | $0.00041 | $0.00779 |
| Sonnet 5 | $0.00016 | $0.00312 |
| Haiku 4.5 | $0.00008 | $0.00156 |
Grade A, and why
code-review-graph 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.
How it starts
The opening of the file, as written. The whole thing — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review Graph — Structural Context over Brute-Force Reading
Instead of letting an assistant read an entire directory to understand a change, hand it a structural map. The graph returns only the files actually connected to what you touched.
What It Is
code-review-graph runs as an MCP server. It uses Tree-sitter to parse source into an abstract syntax tree, stores the resulting nodes and relationships in SQLite, and answers context queries from that graph. Ask "what does changing this file affect?" and it returns the impacted files — the blast radius — rather than the whole tree.
The token savings track codebase size:
| Repo | What to expect |
|---|---|
| Huge monorepo (10K+ files) | Largest win — only a sliver gets read |
| Mid-size app (1–5K files) | Solid reduction on cross-file changes |
| Small project (<200 files) | Marginal — graph upkeep can outweigh it |
Scoping to the blast radius also trims noise, which tends to sharpen review focus. Treat any cited multiplier as illustrative and measure on your own repo.
Deciding Whether to Use It
Lean in when the repo is 500+ files, changes routinely span modules, monthly token spend is meaningful, or you live in monorepo / microservice / cross-package territory.
Skip it when the repo is under ~200 files with self-contained edits, the code leans heavily on dynamic tricks (reflection, runtime codegen, dynamic imports), or you want zero maintenance — the graph must stay in sync to be useful.
Benchmark first when you're in the 200–500 file range or mixing static and dynamic patterns; test on representative commits before committing.
Opt-In Bootstrap
On a mid-to-large project, confirm availability before depending on it:
- Is the tool installed?
Get-Command code-review-graph(Windows) orwhich code-review-graph(Unix). - Does a
.code-review-graph/directory already exist in the workspace? - Installed but no index? Ask before running
code-review-graph build— it scans the whole project. - Not installed and the project is large? Offer to
pip install code-review-graphand build a local map, but never install or build without the user agreeing.
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 · 126 lines · 82 tokens per session scan A 33bf2b33de9b
code-review-graph is a skill published in the GitHub repository phuonghx/aim-cli (1 stars, last pushed 2mo ago), licensed MIT. It adds 82 tokens to every session and 1,558 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
hs-release
Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.
hindsight-local
Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user).
research-repository
Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.
design-negotiation
Advocate for design quality, scope, and timeline with partners and leadership using evidence and shared goals. Use in the conversation itself. For the commercial vocabulary behind it, use business-design (ux-strategy).
user-persona
Build research-grounded personas with goals, frustrations, and behavioural patterns. Use when decisions need a consistent user reference. For one session's emotional snapshot use empathy-map; for motivation framing use jobs-to-be-done.
version-control-strategy
Define version control for design files, components, and libraries — branching, naming, and release. Use when file history is chaotic. For design system contribution rules, use design-system-governance (design-systems).