codd-scan

A tool that rebuilds a CoDD project's dependency graph from its documents and source code. The graph shows which requirements, designs, code and tests are connected.

In plain words
What is it for?
Refreshing project dependencies before checking validity, analysing change impact, generating documentation or verifying links between project artefacts.
Why use it?
It prevents later checks from using outdated project information after files change. It also reports graph counts, document coverage and warnings.

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/yohey-w/codd-dev/codd-scan
Any agent
npx skills add yohey-w/codd-dev --skill codd-scan
Clone the repo
git clone --depth 1 https://github.com/yohey-w/codd-dev

Made for: Claude Code, Codex.

Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,248 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 $0.00058 $0.01248
Opus 5 $0.00029 $0.00624
Sonnet 5 $0.00012 $0.00250
Haiku 4.5 $0.00006 $0.00125

Measured 3d ago against content hash 937b32390ff1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codd-scan 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.

skills/codd-scan/SKILL.md · 124 lines

How it starts

The opening of the file, as written. The whole thing — 124 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CoDD Scan

Refresh the CoDD dependency graph from document frontmatter and source code so later commands (codd validate, codd impact, codd generate, codd verify) operate on current project state. Use this after requirements, design docs, implementation, or tests change.

When to Use

  • After editing Markdown files with CoDD frontmatter
  • After adding or changing source files that affect dependencies
  • Before codd impact when you need a fresh graph
  • When scan counts look stale or unexpectedly low

Preconditions

  1. Resolve the target project root first. Prefer an absolute path when the working directory is ambiguous.
  2. Check whether codd/codd.yaml exists under that path.
  3. If codd/codd.yaml is missing, initialize CoDD before scanning:
codd init --project-name "<project-name>" --language "<language>" --dest <path>
  1. If codd is not on PATH, use one of these:
    • pip install codd-dev
    • .venv/bin/codd scan --path <path>

Command

Run the scan from anywhere by passing the project root explicitly:

codd scan --path <path>

If you are already at the project root, codd scan --path . is sufficient.

What the Scan Does

  1. Reads codd/codd.yaml
  2. Rebuilds auto-generated graph data from project documents and source code
  3. Preserves human-authored evidence
  4. Prints a short summary of frontmatter coverage and graph size

How to Interpret the Result

Typical output includes:

Scan complete:
  Documents with frontmatter: <count>
  Graph: <nodes> nodes, <edges> edges
  Evidence: <total> total (...)
  • Documents with frontmatter: how many Markdown documents in configured doc_dirs were successfully read as CoDD documents. If this is lower than expected, inspect missing frontmatter or wrong doc_dirs.
  • nodes: the number of tracked artifacts in the graph. In document-centric projects this is usually close to the total number of requirements/design/test artifacts being tracked.
  • edges: the total number of declared or inferred dependency relationships between those artifacts.
  • orphan nodes: artifacts that have no surviving dependency relationship. They are often a sign of missing depends_on, stale docs, or a document that should be deleted. Some top-level requirements may be intentional exceptions, but unexplained orphans should always be reviewed.
  • WARNING: lines: scan found suspicious input such as missing frontmatter or design docs with empty dependencies. Treat warnings as a prompt to run codd validate.
  • SCAN_ERROR (if surfaced by your wrapper, report script, or higher-level UI): frontmatter could not be parsed or read cleanly. Treat it as a validation problem and inspect the document with codd validate --path <path>.

Read the full file on GitHub · 124 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.

  1. 3d ago First seen · 124 lines · 58 tokens per session scan A 937b32390ff1

Subscribe to this mod's changes

codd-scan is a skill published in the GitHub repository yohey-w/codd-dev (114 stars, last pushed 22d ago), licensed MIT. It adds 58 tokens to every session and 1,248 once invoked, about $0.0003 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens