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.
npx agentmods add skills/ankitclassicvision/ankit_shared_skills/codebase-organizernpx skills add AnkitClassicVision/ankit_shared_skills --skill codebase-organizergit clone --depth 1 https://github.com/AnkitClassicVision/ankit_shared_skillsWrote 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.
[](https://agentmods.dev/skills/ankitclassicvision/ankit_shared_skills/codebase-organizer)<a href="https://agentmods.dev/skills/ankitclassicvision/ankit_shared_skills/codebase-organizer"><img src="https://agentmods.dev/badge/skills/ankitclassicvision/ankit_shared_skills/codebase-organizer.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00116 | $0.03522 |
| Opus 5 | $0.00058 | $0.01761 |
| Sonnet 5 | $0.00023 | $0.00704 |
| Haiku 4.5 | $0.00012 | $0.00352 |
Grade A, and why
codebase-organizer 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 4d 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.
How it starts
The opening of the file, as written. The whole thing — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
codebase-organizer
One-line pitch
Point it at any repo. Get a structured, skill-like decomposition with deep module scoring, dependency graph, circular dependency detection, orphaned file surfacing, and three-layer context extraction — all saved to .run-project/ for automatic consumption by /run-project, SEEIT, and agent-spec phases.
Invocation
/organize [path]
path: Repo path (defaults to.).- Zero flags. All behavior auto-detected:
- Repo size < 1000 LOC → lightweight scan only
- Repo size >= 1000 LOC → deep analysis enabled
- Existing
.run-project/→ bind to existing pipeline context - Clean repo → produce standalone analysis
When to use it
| Situation | Tool | Why |
|---|---|---|
Starting /run-project on brownfield |
/organize |
Establish baseline architecture before grilling |
| During spec diagramming | /organize |
Inject organized structure into SEEIT |
| Post-refactor audit | /organize |
See what changed, find new hotspots |
| Onboarding new AI agent | /skillify |
Give it .skill-pack/PROJECT.md — a consumable skill manifest |
| Exploring inherited code | /organize |
Quick orientation — deep modules, seams, orphaned files |
| Any time you feel lost in a repo | /skillify |
Re-run. .skill-pack/ stays fresh. |
| Want repo to be consumable by agents | /skillify |
Produces persistent .skill-pack/ that travels with repo |
Pipeline integration (automatic binding)
When .run-project/ exists, the organizer auto-writes to:
.run-project/
context/
structural.json -- module map, import graph, circular deps, orphans
semantic.json -- interfaces, contracts, complexity scores
philosophical.json -- deep modules, hotspots, recommendations
seeit/
modules.json -- spec-diagram injection data
interfaces.json -- entry points + contracts
data-flow.json -- producer → consumer pairs
skill-structure.json -- candidate skill layout (see Part 2b above)
organizer-report.json -- summary for resume-read by /run-project phases
What ships with it
9 files 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.
- references/deep-modules-theory.md 2.5 KB
- references/deepen-pipeline-reference.md 2.5 KB
- references/grilling-guide.md 2.1 KB
- references/interface-patterns.md 2.7 KB
- references/invocation-patterns.md 2.1 KB
- references/run-project-integration.md 37 B
- scripts/discover-rank.py 4.4 KB runs code
- scripts/grill-presentation.py 2.8 KB runs code
- scripts/organize.py 22 KB runs code
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.
- 4d ago First seen · 300 lines · 116 tokens per session scan A 79fd80548283
codebase-organizer is a skill published in the GitHub repository AnkitClassicVision/ankit_shared_skills (11 stars, last pushed 23d ago), licensed MIT. It adds 116 tokens to every session and 3,522 once invoked, about $0.0006 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.
Other skills, from other repositories
explore
Meta-skill for internal codebase exploration at varying depths (quick/deep/architecture).
code-quality-review
Run a maintainability and structure review focused on abstraction quality, branching complexity, file growth, canonical ownership, duplication, and refactoring opportunities. Use when the user asks for code quality review, maintainability review, 代码质量审查, 可维护性审查, or comments about whether the change stays easy to…
refactor
Refactors specified code to improve clarity, reduce duplication, or align with the project's architectural patterns — without changing external behavior. Invoked when the user asks to refactor, clean up, simplify, or restructure code.
arch-optimize
架构优化技能 v3.2：六大衰退风险扫描（R1-R6）、质量度量（MI/CC/健康分）、回归防护。五阶段工作流配 4 个零依赖本地脚本（archscan/depgraph/riskdiagnose/qualitymetrics/regressionguard），全部输出 JSON。在架构审查、技术债评估、代码重构、质量提升、工程结构评审时调用。.
tech-debt-prioritization
Framework for identifying, quantifying and prioritizing technical debt with RICE scoring.
improve-codebase-architecture
Use when surfacing architectural friction inside a single EVOKORE bounded context and proposing deepening refactors (shallow modules, leaky seams, low locality) that turn shallow modules into deep ones — informed by ADR-0005 bounded contexts and the project's domain language.