agentmods.dev

repo-nav

repo-nav is a skill for Claude Code from nitinbhide/tcaitoolkit. It costs 54 tokens per session (8,738 once invoked), scanned A, original, Apache-2.0.

A repository-navigation skill that creates Markdown index files for folders and files. These indexes explain the project structure and guide a coding agent toward the most relevant code and documentation.

In plain words
What is it for?
Use it to generate or update root and folder-level `docmap.md` files that summarize contents, architecture, dependencies, and likely change locations.
Why use it?
Large repositories can be difficult to understand from their file names alone. The indexes provide progressively more detail as an agent moves from the project root into its folders.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions CLAUDE.md; mentions subagents; mentions AGENTS.md.

not rated 5repo changed today A scan 54 tokens original Apache-2.0

Good fit Use it to generate or update root and folder-level docmap.md files that summarize contents, architecture, dependencies, and likely change locations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nitinbhide/tcaitoolkit/repo-nav
View source ↗ nitinbhide/tcaitoolkit
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 nitinbhide/tcaitoolkit --skill repo-nav
Clone the repo
git clone --depth 1 https://github.com/nitinbhide/tcaitoolkit

Made for: Claude Code.

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.

agentmods badge for repo-nav

README.md
[![agentmods](https://agentmods.dev/badge/skills/nitinbhide/tcaitoolkit/repo-nav/github.svg)](https://agentmods.dev/skills/nitinbhide/tcaitoolkit/repo-nav)
Your own site
<a href="https://agentmods.dev/skills/nitinbhide/tcaitoolkit/repo-nav"><img src="https://agentmods.dev/badge/skills/nitinbhide/tcaitoolkit/repo-nav/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.

agentmods 80×15 button for repo-nav

Your own site · 80×15
<a href="https://agentmods.dev/skills/nitinbhide/tcaitoolkit/repo-nav"><img src="https://agentmods.dev/badge/skills/nitinbhide/tcaitoolkit/repo-nav.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,738 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.
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 5.1 $0.00054 $0.08738
Opus 5.5 $0.00022 $0.03495
Sonnet 5.5 $0.00011 $0.01748
Haiku 4.5 $0.00005 $0.00874

Measured today against content hash beaef4364418, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

repo-nav 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 today.

The scan reads SKILL.md. This mod also ships 10 executable files (evals/slippers/test.py, scripts/detect_db.ps1, scripts/detect_db.sh, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

agentskills/repo-nav/SKILL.md · 527 lines

How it starts

The opening of the file, as written. The whole thing — 527 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Project Repository Navigation Index Generation Skill

Purpose

Analyze a software repository and generate a hierarchy of index files that enables AI coding agents to rapidly understand the repository structure, architecture, implementation details, business features, dependencies, and change impact.

This skill only generates index files and is not to be used by coding agents for project decision making.

Generate Markdown index files (DOCMAP.md at root, docmap.md in each folder) that summarize the contents of a local repository using progressive disclosure.

Progressive Disclosure principle:

  1. A coding agent should be able to understand the repository at a high level by reading a small number of files.
  2. The agent should be guided toward the most relevant folders and files.
  3. Detailed information should only appear at deeper levels of the hierarchy.
  4. Each index/docmap should help the agent decide what to read next.
  5. Each index should help the agent decide what files are likely to require modification.
  6. Each child index must provide greater detail than its parent.
  7. Each parent index must summarize child content.

The primary consumers of the generated indexes are AI coding agents.

DO NOT deviate from this SKILL instructions during the execution of the repo-nav workflow.

Reference Workflow and Tools

  • Use PowerShell on Windows and Bash on Unix-like systems.
  • For a user-oriented explanation of project roots, docmaps, checkpoints, and common prompts, see references/help.md.
  • If the user asks for help, present the contents of references/help.md first. After presenting it, check whether rg is available before proceeding with any other repo-nav operation; if it is unavailable, follow the instructions below.
  • rg (ripgrep) is a hard prerequisite for this skill. Do not begin repository discovery, inventory creation, or docmap generation until rg is confirmed available.
  • Use the reference files in this section as part of the workflow.
    • First check whether rg is available, then follow references/ripgrepsearch.md for repository discovery, retained inventories, content searches, and rg-based validation.
    • When PowerShell is the selected shell, also follow references/powershell.md for path handling and shell-side validation operations.
    • When Bash is the selected shell on a Unix-like system, also follow references/bash.md for path handling and shell-side validation operations.

Read the full file on GitHub · 527 lines

Files

What ships with it

20 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.

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. today Changed · +1 lines beaef4364418
  2. yesterday Changed · +8 lines a9f8fb4371d3
  3. 2d ago Changed · +19 lines 221cafd4ffbe
  4. 19d ago Changed · +53 lines · +20 tokens per session 7817441cfcef
  5. 23d ago Changed · +3 lines 4dcf8a104738
  6. 1mo ago Changed · +1 lines a97929d58f9a
  7. 1mo ago Changed · +5 lines 30066cd57fdc
  8. 1mo ago Changed · +1 lines 31cf92cec3e8
  9. 1mo ago Changed · +3 lines 852b3e94c851
  10. 1mo ago First seen · 433 lines · 34 tokens per session scan A d60674eb4431

Subscribe to this mod's changes

repo-nav is a skill published in the GitHub repository nitinbhide/tcaitoolkit (5 stars, last pushed today), licensed Apache-2.0. It adds 54 tokens to every session and 8,738 once invoked, about $0.0002 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 2026-09-11.

Writing and docscodebase-analysisindexingrepository-structure
Related

repo-nav compared with skills from other repositories

repo-nav next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
repo-navnitinbhide/tcaitoolkitSkill5todayApache-2.0A54Claude Code
agents-generatorsickn33/agentic-awesome-skillsSkill49kyesterdayMITA50Claude Code
target-connectorcocoindex-io/cocoindexSkill12ktodayApache-2.0A52Claude Code, Codex
create-releasecocoindex-io/cocoindexSkill12ktodayApache-2.0A202Claude Code, Codex
cocoindexcocoindex-io/cocoindexSkill12ktodayApache-2.0A88Claude Code, Codex
cocoindex-diagramscocoindex-io/cocoindexSkill12ktodayApache-2.0A124Claude Code, Codex
backportcocoindex-io/cocoindexSkill12ktodayApache-2.0A119Claude Code, Codex