A benchmarking guide for measuring whether CodeGraph helps an AI coding agent find relevant code in a real software repository. It compares the agent’s results with CodeGraph against results from ordinary search and file reading.

Use it to choose a CodeGraph version, programming language, and repository, run the comparison, and report the results.

It provides a repeatable way to check whether a particular CodeGraph version genuinely improves code retrieval instead of assuming it does.

How colbymchenry/codegraph configures Claude Code

About the project

CodeGraph is a local, pre-indexed knowledge graph of a software codebase that helps AI coding agents understand relationships across files and symbols. Developers use it to retrieve focused code context, keep the graph synchronized with changes, and support agents such as Claude Code, Codex, Cursor, and Gemini. The catalogue entries provide CodeGraph skills and instructions for those agent workflows.

colbymchenry/codegraph · 75,627 stars · on GitHub · colbymchenry.github.io

Reuse

Borrowing it

Nothing to install: this file belongs to colbymchenry/codegraph. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/colbymchenry/codegraph/main/.claude/skills/agent-eval/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/colbymchenry/codegraph

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/colbymchenry/codegraph/agent-eval/github.svg)](https://agentmods.dev/skills/colbymchenry/codegraph/agent-eval)

Your own site

<a href="https://agentmods.dev/skills/colbymchenry/codegraph/agent-eval"><img src="https://agentmods.dev/badge/skills/colbymchenry/codegraph/agent-eval/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/colbymchenry/codegraph/agent-eval"><img src="https://agentmods.dev/badge/skills/colbymchenry/codegraph/agent-eval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 65 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,016 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

Socket pass 5 Aug 2026
Snyk pass 5 Aug 2026
NVIDIA SkillSpector pass 7 Sept 2026

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

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	$0.00065	$0.01016
Opus 5.5	$0.00026	$0.00406
Sonnet 5.5	$0.00013	$0.00203
Haiku 4.5	$0.00006	$0.00102

Measured 1mo ago against content hash 26c1bba3df4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agent-eval 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.

Origin

Copies of this mod

4 near-identical copies found in the catalogue:

agent-eval — 92% identical, 6 lines differ
agent-eval — 92% identical, 6 lines differ
agent-eval — 92% identical, 6 lines differ
agent-eval — 86% identical, 38 lines differ

.claude/skills/agent-eval/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeGraph Quality Audit

Measures how much CodeGraph helps an agent versus plain grep/read, for a chosen codegraph version on a chosen real-world repo. Drives the harness in scripts/agent-eval/.

Prerequisites

tmux 3+, a logged-in claude CLI, node, git (macOS/Linux).
Run from the codegraph repo root.

Workflow

Copy this checklist:

- [ ] 1. Pick version (local or npm)
- [ ] 2. Pick language
- [ ] 3. Pick repo by size
- [ ] 4. Pick harness (headless / tmux / both)
- [ ] 5. Run audit.sh in the background
- [ ] 6. Report results

Step 1 — version. Ask with AskUserQuestion: which codegraph version to test. Offer "Local dev build" and "Latest published"; the free-text "Other" lets the user type a specific version (e.g. 0.7.10). Map the answer to a VERSION token:

"Local dev build" → local
"Latest published" → latest
a typed version → that string (e.g. 0.7.10)

Step 2 — language. Read .claude/skills/agent-eval/corpus.json. Ask with AskUserQuestion which language to test, listing the languages that have entries.

Step 3 — repo. From the chosen language's entries, ask which repo. Label each option with its size and file count, e.g. excalidraw — Medium (~600 files). Each entry carries the repo URL and a representative question.

Step 4 — harness. Ask with AskUserQuestion which harness to run, and map the answer to a MODE token:

"Headless" → headless — claude -p with stream-json: exact tokens/cost and a clean tool sequence (2 runs, fast, no TTY).
"Interactive (tmux)" → tmux — drives the real Claude TUI in tmux: faithful Explore-subagent behavior, metrics from session logs (2 runs, slower).
"Both" → all — headless + interactive (4 runs).

Step 5 — run. Launch in the background (sets the version, clones if missing, wipes + re-indexes, runs the chosen arms — several minutes):

scripts/agent-eval/audit.sh <VERSION> <repo-name> <repo-url> "<question>" <MODE>

Step 6 — report. When the job finishes, read the log and report per arm:

Headless (parse-run.mjs): total tool calls, file Reads, Grep/Bash, codegraph-tool calls, duration, total cost.
Interactive (parse-session.mjs): the VERDICT: codegraph_explore used Nx | Read N | Grep/Bash N and TOKENS: lines.
Both paths also print the three feedback metrics — residual context occupancy, explore sufficiency, allocation efficiency — and a headless A/B ends with a side-by-side ARM COMPARISON table. Report that table, and check its contamination row first: CLI calls that RETURNED output > 0 means the arm reached codegraph through Bash and its numbers are void. How to read the rest: docs/benchmarks/agent-eval-feedback-metrics.md.

Read the full file on GitHub · 81 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

corpus.json 22 KB

Changes

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 · 81 lines · 65 tokens per session scan A 26c1bba3df4e

Subscribe to this mod's changes

agent-eval is a skill published in the GitHub repository colbymchenry/codegraph (75,627 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 1,016 once invoked, about $0.0003 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 2026-08-30.

Analytics and metrics Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

cua-driver

Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.

davidondrej/skills · 68 tokens

codegraph: Skill for Claude Code