Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
colbymchenry avatar

Agent Eval

  • 1.4k installs
  • 64.6k repo stars
  • Updated August 1, 2026
  • colbymchenry/codegraph

agent-eval provides documented workflows for Benchmark CodeGraph retrieval quality on a real codebase by comparing agent behavior with vs without CodeGraph. Use when the user runs /agent-eval or asks to te

About

The agent-eval skill benchmark CodeGraph retrieval quality on a real codebase by comparing agent behavior with vs without CodeGraph. Use when the user runs /agent-eval or asks to test, benchmark, audit, or validate a codegraph version (the local dev build or a published npm version) against a language's repo. # 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 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.

  • `tmux` 3+, a logged-in `claude` CLI, `node`, `git` (macOS/Linux).
  • Run from the codegraph repo root.
  • [ ] 1. Pick version (local or npm)
  • [ ] 2. Pick language
  • [ ] 3. Pick repo by size

Agent Eval by the numbers

  • 1,390 all-time installs (skills.sh)
  • +38 installs in the week ending Aug 5, 2026 (Skillselion tracking)
  • Ranked #226 of 2,715 Automation & Workflows skills by installs in the Skillselion catalog
  • Security screen: MEDIUM risk (skills.sh audit)
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
At a glance

agent-eval capabilities & compatibility

Capabilities
`tmux` 3+, a logged in `claude` cli, `node`, `gi · run from the codegraph repo root. · [ ] 1. pick version (local or npm) · [ ] 2. pick language · [ ] 3. pick repo by size
Use cases
documentation
From the docs

What agent-eval says it does

# 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.
SKILL.md
Drives the harness in `scripts/agent-eval/`.
SKILL.md
npx skills add https://github.com/colbymchenry/codegraph --skill agent-eval

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs1.4k
repo stars64.6k
Security audit2 / 3 scanners passed
Last updatedAugust 1, 2026
Repositorycolbymchenry/codegraph

How do I use agent-eval for the task described in its SKILL.md triggers?

Benchmark CodeGraph retrieval quality on a real codebase by comparing agent behavior with vs without CodeGraph. Use when the user runs /agent-eval or asks to test, benchmark, audit, or validate a cod.

Who is it for?

Teams invoking agent-eval when the user request matches documented triggers and prerequisites.

Skip if: Skip when cached docs are missing, the request is a negative trigger, or another sibling skill owns the workflow.

When should I use this skill?

Benchmark CodeGraph retrieval quality on a real codebase by comparing agent behavior with vs without CodeGraph. Use when the user runs /agent-eval or asks to test, benchmark, audit, or validate a codegraph version (the l

What you get

Step-by-step guidance grounded in agent-eval documentation and reference files.

  • With-vs-without CodeGraph benchmark report
  • Per-version retrieval quality audit results

By the numbers

  • Requires tmux version 3 or newer alongside claude CLI, node, and git
  • Uses harness located at scripts/agent-eval/ inside the codegraph repository

Files

SKILL.mdMarkdownGitHub ↗

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" → headlessclaude -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.

Lead with cost + tool/Read counts — they are the reliable signals; raw token in/out are confounded by subagent delegation and prompt caching. State whether codegraph reduced effort and whether both arms reached a correct answer.

Notes

  • The index is rebuilt every run (audit.sh wipes .codegraph) — different

versions extract differently, so an index must be served by the same binary that built it.

  • audit.sh temporarily mutates the global codegraph install for the test,

then restores your dev link via local-install.sh.

  • Corpus repos are cloned to /tmp/codegraph-corpus (reused if already present).
  • Add or edit repos in corpus.json (fields: name, repo, size, files,

question).

Related skills

How it compares

Pick agent-eval when you need side-by-side CodeGraph versus baseline agent measurements on a real repo instead of synthetic unit tests alone.

FAQ

What does agent-eval do?

Benchmark CodeGraph retrieval quality on a real codebase by comparing agent behavior with vs without CodeGraph. Use when the user runs /agent-eval or asks to test, benchmark, audit, or validate a codegraph version (the l

When should I use agent-eval?

Benchmark CodeGraph retrieval quality on a real codebase by comparing agent behavior with vs without CodeGraph. Use when the user runs /agent-eval or asks to test, benchmark, audit, or validate a codegraph version (the l

What are common prerequisites?

--- name: agent-eval description: Benchmark CodeGraph retrieval quality on a real codebase by comparing agent behavior with vs without CodeGraph.

Is Agent Eval safe to install?

skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.