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 skills add jellydn/my-ai-tools --skill codemapgit clone --depth 1 https://github.com/jellydn/my-ai-toolsWrote 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/jellydn/my-ai-tools/codemap)<a href="https://agentmods.dev/skills/jellydn/my-ai-tools/codemap"><img src="https://agentmods.dev/badge/skills/jellydn/my-ai-tools/codemap/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.
<a href="https://agentmods.dev/skills/jellydn/my-ai-tools/codemap"><img src="https://agentmods.dev/badge/skills/jellydn/my-ai-tools/codemap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00019 | $0.02756 |
| Opus 5.5 | $0.00008 | $0.01102 |
| Sonnet 5.5 | $0.00004 | $0.00551 |
| Haiku 4.5 | $0.00002 | $0.00276 |
Grade A, and why
codemap 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 20d 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 — 310 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codemap
What I do
Analyze your entire codebase and create 7 comprehensive documentation files in .planning/codebase/:
- STACK.md - Technologies, dependencies, configuration
- INTEGRATIONS.md - 3rd party providers, APIs, databases, auth providers
- ARCHITECTURE.md - System patterns, layers, data flow
- STRUCTURE.md - Directory layout, key locations, naming conventions
- CONVENTIONS.md - Code style, patterns, error handling
- TESTING.md - Framework, structure, mocking, coverage
- CONCERNS.md - Tech debt, bugs, security, performance issues
When to use me
Use this skill when you need to:
- Onboard new developers to understand the codebase quickly
- Plan new features with full context of existing patterns
- Understand code conventions before making changes
- Identify technical debt and areas of concern
- Document the current state of the project
How it works
This skill runs four focus passes. Use parallel file-reading and file-writing workers when the runtime provides them. If suitable workers are unavailable, perform the same passes sequentially in the current context:
- Tech → Analyzes stack and integrations → STACK.md, INTEGRATIONS.md
- Architecture → Analyzes patterns and structure → ARCHITECTURE.md, STRUCTURE.md
- Quality → Analyzes conventions and testing → CONVENTIONS.md, TESTING.md
- Concerns → Identifies tech debt and issues → CONCERNS.md
Each pass:
- Explores the codebase for its focus
- Uses templates from
$SKILL_PATH/templates/ - Writes documents directly to
.planning/codebase/ - Returns only confirmation (not document contents)
The orchestrator:
- Creates
.planning/codebase/directory - Runs the four passes in parallel only when suitable workers are available
- Otherwise runs those passes sequentially in the current context
- Collects confirmations
- Verifies all documents created
- Commits the codebase map (if configured)
Process
Scope and Runtime
Accept an optional --paths <p1,p2,...> for an incremental map. Validate repository-relative prefixes before use: reject absolute paths, .. components, and shell metacharacters (;, backticks, $, &, |, <, >). If no supplied path is valid, stop and ask for a corrected scope; do not silently expand to the whole repository. Pass the same normalized scope to every mapper and every sequential pass. Do not interpolate unchecked input into shell commands.
What ships with it
7 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.
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.
- 20d ago Changed · +19 lines 73d8f630d94a
- 1mo ago Changed · -3 tokens per session 3d891f5e0d88
- 1mo ago First seen · 291 lines · 22 tokens per session scan A 489017623cc7
codemap is a skill published in the GitHub repository jellydn/my-ai-tools (124 stars, last pushed today), licensed MIT. It adds 19 tokens to every session and 2,756 once invoked, about $0.0001 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.
Other skills, from other repositories
ask-first
A decision guide for handling unclear requests before taking action. It uses one focused question or probe when the requested goal, context, or boundaries are not clear.
insight-miner
A manually triggered writing guide that turns notes, debugging records, design summaries, code snippets, or rough drafts into Chinese technical blog posts. It first identifies and evaluates possible article topics before writing.
book-recommender
A Chinese-language book recommendation and analysis skill that evaluates what books are about, whether they are worth reading, and how to read them.
notes-to-blog
A manually triggered guide for turning technical notes and rough material into a Chinese programming blog post. It first extracts and evaluates the main transferable idea, then writes the article after the user confirms its direction.
wisdom-decoder
A guided explanation skill for ideas from Buddhism, philosophy, and psychology. It presents a chosen topic in everyday language and connects it to practical actions, sources, and perspectives from other fields.
teach-me
A five-step teaching workflow for introducing an unfamiliar topic and guiding the learner toward applying it. It moves from an example and explanation to supported practice and an independent task.