A full testing process for a released codegraph package, a tool that analyses relationships in source code. It installs the package, exercises its commands, compares analysis engines, and records bugs in a report.

Testing stable or development releases, comparing engines, finding defects, and writing a dogfooding report.

It reveals problems in an actual release and checks whether different analysis engines behave consistently.

dogfood — Skill by optave

Install

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.

agentmods

npx agentmods add skills/optave/ops-codegraph-tool/dogfood

Any agent

npx skills add optave/ops-codegraph-tool --skill dogfood

Clone the repo

git clone --depth 1 https://github.com/optave/ops-codegraph-tool

Made for: Claude Code, Codex.

Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 7,598 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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	$0.00046	$0.07598
Opus 5	$0.00023	$0.03799
Sonnet 5	$0.00009	$0.01520
Haiku 4.5	$0.00005	$0.00760

Measured 2d ago against content hash 92dbf45667e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

dogfood 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.

.claude/skills/dogfood/SKILL.md · 566 lines

How it starts

The opening of the file, as written. The whole thing — 566 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Dogfooding Session for @optave/codegraph@$ARGUMENTS

You are running a comprehensive dogfooding session for codegraph v$ARGUMENTS. Your goal is to install the published package, exercise every feature, compare engines, find bugs, and produce a structured report.

Reference: Read generated/dogfood/DOGFOOD-REPORT-2.1.0.md and generated/dogfood/DOGFOOD_REPORT_v2.2.0.md (if present) for the format and depth expected. Match or exceed that quality.

Phase 0 — Setup

Create a temporary working directory (e.g., /tmp/dogfood-$ARGUMENTS or a system temp).

Install the package — the method depends on whether this is a stable or dev version:

Stable release (version does NOT contain -dev., e.g. 2.5.1):

npm init -y && npm install @optave/codegraph@$ARGUMENTS

Dev build (version contains -dev., e.g. 3.1.6-dev.12): Dev builds are not published to npm. They are attached as tarballs to GitHub pre-releases. Install from the GitHub release:

npm init -y

# Main package
npm install https://github.com/optave/ops-codegraph-tool/releases/download/dev-v$ARGUMENTS/optave-codegraph-$ARGUMENTS.tgz

# Platform-specific native binary (pick one for the current platform):
# Windows x64:
npm install https://github.com/optave/ops-codegraph-tool/releases/download/dev-v$ARGUMENTS/optave-codegraph-win32-x64-msvc-$ARGUMENTS.tgz
# macOS ARM:
npm install https://github.com/optave/ops-codegraph-tool/releases/download/dev-v$ARGUMENTS/optave-codegraph-darwin-arm64-$ARGUMENTS.tgz
# macOS x64:
npm install https://github.com/optave/ops-codegraph-tool/releases/download/dev-v$ARGUMENTS/optave-codegraph-darwin-x64-$ARGUMENTS.tgz
# Linux x64:
npm install https://github.com/optave/ops-codegraph-tool/releases/download/dev-v$ARGUMENTS/optave-codegraph-linux-x64-gnu-$ARGUMENTS.tgz

Tip: To find the latest dev version, run:

gh release list --repo optave/ops-codegraph-tool --json tagName --jq '.[] | select(.tagName | startswith("dev-v")) | .tagName' | head -1 | sed 's/^dev-v//'

Read the full file on GitHub · 566 lines

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.

2d ago First seen · 566 lines · 46 tokens per session scan A 92dbf45667e1

Subscribe to this mod's changes

dogfood is a skill published in the GitHub repository optave/ops-codegraph-tool (92 stars, last pushed yesterday), licensed Apache-2.0. It adds 46 tokens to every session and 7,598 once invoked, about $0.0002 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.

Debugging Git and workflow Testing ai-agents cli code-analysis dependency-graph impact-analysis incremental-builds

codespaces

Build and query architecture-aware code search, dependency graphs, call flows, impact analysis, and belief maps for Python, TypeScript, TSX, Rust, C#, Java, Go, Ruby, and Ruby on Rails repositories. Use before non-trivial code changes to find module boundaries, blast radius, architecture violations, and the minimal…

diskd-ai/codespaces · 74 tokens

security-triage

Turn a large codebase into a short, ranked reading list of security-relevant code paths worth a human researcher's time, using the flyto-indexer MCP tools. Use when asked to find, prioritize, or triage potential vulnerabilities / taint flows / attack surface in a repository indexed (or indexable) by flyto-indexer …

flytohub/flyto-indexer · 105 tokens

devlens

Understand a codebase with the DevLens MCP — TypeScript, JavaScript, Python, Go, Rust, or Java (incl. React/Next.js/Node, FastAPI/Flask/Django, Spring Boot, Gin/Echo/chi/net-http, axum/actix/rocket). Query a precomputed graph of nodes (components, hooks, functions, classes, methods, structs, traits, routes) and typed…

devlensio/devlensOSS · 0 tokens

archon

Multi-language dependency impact analysis for Java, JS/TS, and Python codebases. Answers "if I change this, what breaks?" Run /archon diff before refactoring, /archon analyze for full dependency maps.

Schr0d/Archon · 48 tokens

codebase-intelligence

Query the codebase-intelligence CLI to understand TypeScript architecture, dependencies, blast radius, and risk before reading files. Use for any "how is this structured", "what breaks if I change X", "where is the complexity" question.

bntvllnt/codebase-intelligence · 54 tokens

repomix

Pack and analyze codebases into AI-friendly single files using Repomix. Use when the user wants to explore repositories, analyze code structure, find patterns, check token counts, or prepare codebase context for AI analysis. Supports both local directories and remote GitHub repositories.

yamadashy/repomix · 58 tokens