A project feature map stored as a JSON file, showing what the software does as epics, features, and smaller steps. It keeps the map aligned with the project as code and specifications change.

Use it to scan a project, refresh its feature map, or synchronize the map after completing code changes.

It provides a current view of the product's functionality, making it easier to understand what exists and what changed without reading the entire codebase.

codesee — Skill for Claude Code and Codex by Kaka-cheaper

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.

Any agent

npx skills add Kaka-cheaper/codeSee --skill templates

Clone the repo

git clone --depth 1 https://github.com/Kaka-cheaper/codeSee

Made for: Claude Code, Codex.

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/kaka-cheaper/codesee/templates/github.svg)](https://agentmods.dev/skills/kaka-cheaper/codesee/templates)

Your own site

<a href="https://agentmods.dev/skills/kaka-cheaper/codesee/templates"><img src="https://agentmods.dev/badge/skills/kaka-cheaper/codesee/templates/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/kaka-cheaper/codesee/templates"><img src="https://agentmods.dev/badge/skills/kaka-cheaper/codesee/templates.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,101 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

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	$0.00088	$0.01101
Opus 5.5	$0.00035	$0.00440
Sonnet 5.5	$0.00018	$0.00220
Haiku 4.5	$0.00009	$0.00110

Measured 1mo ago against content hash 394ba77009ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codesee 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.

templates/SKILL.md · 85 lines

How it starts

The opening of the file, as written. The whole thing — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CodeSee Skill

Keep .codesee/features.json in sync with the project's actual functionality. The graph captures what the project does, not how, at three levels: Epic → Feature → Step.

When to activate

The user says "scan", "sync codesee", "refresh feature map", "更新功能图", or similar
After completing a code change in a project that has .codesee/ or AGENTS.md mentioning CodeSee
When .codesee/features.json is missing/empty in a project that should have it

Quick decision tree

1. Is .codesee/features.json missing or empty?
   YES → Run first-time scan: read .codesee/prompts/scan.md
   NO  → Continue to step 2

2. Did you just complete a code change?
   YES → Run incremental sync: read .codesee/prompts/sync.md
   NO  → Continue to step 3

3. Did the user explicitly ask to refresh?
   YES → Read .codesee/prompts/scan.md (force re-scan)
   NO  → Skip activation

Project-stage awareness

scan.md auto-detects which sub-mode to use:

SDD project (has .specify/, .trellis/, .bmad-core/, .agents/skills/) → scan-sdd.md (forward projection from spec/PRD)
Code-only light (< 100 source files) → scan-light.md
Code-only heavy (≥ 100 source files) → scan-heavy.md (4-phase)
Doc-only / planning (no code yet) → scan-planning.md

Don't pick the sub-mode yourself. Read scan.md first; it routes for you.

Hard constraints (MUST)

Never modify files under .codesee/prompts/ or .codesee/scripts/
Never modify a feature with locked: true
Never rename existing IDs (deprecate via tags: ['deprecated'] instead)
Always run node .codesee/scripts/validate-features.mjs after writing — exit code 1 must be fixed
flow.kind is required on every flow edge
step.name must be a verb phrase in the language specified by manifest.lang

See .codesee/prompts/_rules.md for the full constraint hierarchy (MUST / SHOULD / MAY).

Checkpoint protocol (large tasks)

If the user's task touches 5+ files, don't wait until the end to sync. Split into logical closures (a "closure" = a user-perceivable, independently verifiable feature) and run sync.md after each. After all closures done, do a final integrity check (coverage / relations / epic_flow / refs / validator). See .codesee/prompts/sync.md § Checkpoint protocol.

Read the full file on GitHub · 85 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.

AGENTS-snippet.md 3.1 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 · 85 lines · 88 tokens per session scan A 394ba77009ac

Subscribe to this mod's changes

codesee is a skill published in the GitHub repository Kaka-cheaper/codeSee (57 stars, last pushed 3mo ago), licensed MIT. It adds 88 tokens to every session and 1,101 once invoked, about $0.0004 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.

Planning ai-agent developer-tools react-flow semantic-graph visualization

tensorboard

Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit.

davila7/claude-code-templates · 32 tokens

academic-plotting

Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn.…

Orchestra-Research/AI-Research-SKILLs · 68 tokens

experiment-tracking-swanlab

Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media logging for ML workflows.

Orchestra-Research/AI-Research-SKILLs · 40 tokens

infographic-creator

An information-graphic creation guide that turns written information into a visual layout using AntV Infographic, a description language for rendering infographics.

antvis/Infographic · 25 tokens

results-analysis

This skill should be used when the user asks to "analyze experimental results", "run strict statistical analysis", "compare model performance", "generate scientific figures", "check significance", "do ablation analysis", or mentions interpreting experiment data with rigorous statistics and visualization. It focuses on…

Galaxy-Dawn/claude-scholar · 68 tokens

data-viz-renderer

Generate self-contained HTML/SVG infographics from JSON data, including stat cards, bar charts, flow diagrams, and mixed dashboards. Offers 8 color palettes and built-in icons with no external dependencies. Triggered when users request data visualization, infographics, charts, or dashboards.

zebbern/claude-code-guide · 62 tokens