agent-eval
/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 local dev build or a published npm version) against a language's repo.
- Author
- EthanYoQ ↗
- Repository
- Skill-hub ↗
- Licence
- MIT
- Last repository change
- 18.10.2026
Assessment and security
- Files in this package
- 2
- Scripts
- 0
- HTML comments
- 0
- URLs in SKILL.md
- 0
No signals detected. Repository changed on 18.10.2026, without references to retired models or APIs.
MIT, open: use and modify while retaining author attribution.
What it does and when to use it
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.
Original author description
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.
How it works
- Prerequisites
- Workflow
- Notes
SKILL.md preview
--- name: agent-eval description: 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 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): ```bash 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 `Read`s, 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`).
Files in this package (2)
- SKILL.md 3 KB
- corpus.json 22 KB
Versions
| Repository | Score | Licence |
|---|---|---|
| This page · EthanYoQ/Skill-hub | 100 | MIT |
| ericrisco/rsc-harness | 100 | MIT |
| colbymchenry/codegraph | 100 | MIT |
| affaan-m/ECC | 100 | MIT |
| SHRIJANAGAIN/Nemo-Cli | 100 | Apache-2.0 |
| ghvinashvili/specagent | 100 | Apache-2.0 |
| bdfinst/agentic-dev-team | 95 | MIT |
Identical content appears in 1 other GitHub folders. We show one copy with the highest score.
Database snapshot: 13.11.2026 · package version df9270a4e0c3 (SHA-256 digest of the entire package)
Downloads in the last 30 days: 0 · ranking
Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.
Similar skills
- 90codegraph-usage
How to use CodeGraph well — which tool answers which question, when to reach for it and when not, and the gotchas that trip agents up. Read before using CodeGraph tools in a project that has a .codegraph/ index, and whenever a CodeGraph call returns confusing or incomplete results. - 86codegraph
Configure or refresh CodeGraph for UCCIF in Codex. Use for $uccif:codegraph, indexing or reindexing a project. Ask before installing missing dependencies. - 100add-lang
Add tree-sitter language support to codegraph end-to-end — wire the grammar + extractor, write tests, then benchmark extraction quality and retrieval value on 3 popular real-world repos. Use when the user runs /add-lang <language> or asks to add/support a new language (e.g. Lua,… - 100add-lang
Add tree-sitter language support to codegraph end-to-end — wire the grammar + extractor, write tests, then benchmark extraction quality and retrieval value on 3 popular real-world repos. Use when the user runs /add-lang <language> or asks to add/support a new language (e.g. Lua,… - 90codegraph
Use when a project has a `.codegraph/` index and you need structural code intelligence — who calls a symbol, what breaks if you change it, where a symbol is defined, or how X reaches Y — instead of grep; also when enabling codegraph in a new project, or unsure which queries are… - 90codegraph-ast-grep
Set up, update, or diagnose CodeGraph and ast-grep so coding agents can use semantic repository scope and structural syntax evidence automatically. Use when a repository needs an idempotent CodeGraph/ast-grep installation, stable tool and index migrations, MCP reconnection,…