ccg-analyze

A deep, explicitly requested analysis workflow for algorithms, feature pipelines, and code relationships using a bounded code relationship graph. It also traces callers, callees, changes, stored flows, and cross-namespace references.

In plain words
What is it for?
Tracing feature flows, mapping impact radius, inspecting callers and callees, and reviewing risks from a git change.
Why use it?
It helps estimate what code and behavior may be affected by a change when ordinary code lookup is not enough.

Skill for Claude CodeCodex

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/tae2089/code-context-graph/ccg-analyze
Any agent
npx skills add tae2089/code-context-graph --skill ccg-analyze
Clone the repo
git clone --depth 1 https://github.com/tae2089/code-context-graph

Made for: Claude Code, Codex.

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 179 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.

ModelPer sessionOnce invoked
Fable 5 $0.00087 $0.00179
Opus 5 $0.00044 $0.00089
Sonnet 5 $0.00017 $0.00036
Haiku 4.5 $0.00009 $0.00018

Measured 3d ago against content hash 94d63af15c6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

ccg-analyze 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 3d 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.

.agents/skills/ccg-analyze/SKILL.md · 14 lines

What it actually says

CCG Analyze Runtime Adapter

Proceed only when the user explicitly names ccg-analyze in the current request. Read the canonical CCG analyze skill completely before acting. Resolve its linked resources relative to the canonical skill directory and follow its analysis boundary and completion instructions for the current task.

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.

  1. 3d ago First seen · 14 lines · 87 tokens per session scan A 94d63af15c6d

Subscribe to this mod's changes

ccg-analyze is a skill published in the GitHub repository tae2089/code-context-graph (17 stars, last pushed 11d ago), licensed MIT. It adds 87 tokens to every session and 179 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 2026-08-30.

Related

Other skills, from other repositories

nopua

The anti-PUA. Drives AI with wisdom, trust, and inner motivation instead of fear and threats. Activates on: task failed 2+ times, about to give up, suggesting user do it manually, blaming environment unverified, stuck in loops, passive behavior, or user frustration ('try harder', 'figure it out', '换个方法', '为什么还不行').…

wuji-labs/nopua · 90 tokens

roadmap

Read the feature roadmap, find the next unplanned phase, brainstorm it, and update the roadmap with the resulting document name.

Ovid/paad · 27 tokens

paad-help

Use when the user asks which paad skills exist, what a paad skill does, which one fits their situation, or how to invoke one — including "what can paad do", "list the paad skills", "is there a paad skill for X", or a request for the arguments of a named paad skill.

Ovid/paad · 71 tokens

release

Cut a paad release — pick the semver bump from what is in [Unreleased], run make release, merge, tag, and verify the published plugin.

Ovid/paad · 34 tokens

backlog

EXPERIMENTAL. Use when working the project-wide out-of-scope backlog at paad/code-reviews/backlog.md — cleaning it of entries that are already fixed or gone, or picking the next entry and fixing it end-to-end. Not for producing backlog entries — that is /agentic-review — and not for reviewing a branch diff.

Ovid/paad · 73 tokens

makefile

Use when creating or updating a Makefile for a project, especially when standard targets (build, test, lint, format, etc.) are missing or when modifying targets that may already be wired into other tooling. Not for debugging why a build fails.

Ovid/paad · 53 tokens