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 iantbutler01/code_diver --skill dive-taggit clone --depth 1 https://github.com/iantbutler01/code_diverWrote 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/iantbutler01/code_diver/dive-tag)<a href="https://agentmods.dev/skills/iantbutler01/code_diver/dive-tag"><img src="https://agentmods.dev/badge/skills/iantbutler01/code_diver/dive-tag/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/iantbutler01/code_diver/dive-tag"><img src="https://agentmods.dev/badge/skills/iantbutler01/code_diver/dive-tag.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00026 | $0.00787 |
| Opus 5.5 | $0.00010 | $0.00315 |
| Sonnet 5.5 | $0.00005 | $0.00157 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade A, and why
dive-tag 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 2mo 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dive Tag
Goal
Maintain a lightweight, cumulative knowledge graph while coding by:
- Adding
@divecomments near meaningful logic - Maintaining project metadata in
.dive/overview.mdand.dive/modules/*.md
Use this skill automatically whenever you modify code.
Required Outputs
1) File-level headers
At the top of any source file you create or substantially modify, add:
@dive-file: <what this file is responsible for>
@dive-rel: <relationship to another file/module/dependency>
@dive-rel: <another relationship, if relevant>
Comment syntax must match the language:
- Rust/JS/TS/Go/Java/C/C++/C#:
// - Python/Shell/Ruby/YAML/TOML:
# - HTML/XML/Markdown:
<!-- -->
Examples:
// @dive-file: Validates JWT tokens and creates auth context for requests.
// @dive-rel: Called by src/api/middleware.rs for every authenticated route.
// @dive-rel: Uses src/auth/session.rs to reject revoked sessions.
2) Inline tags
Add @dive: comments for non-trivial logic you write or change.
Format:
@dive: <plain-English behavior and outcome>
Good:
@dive: Normalizes user input so lookup is case-insensitive@dive: Retries DB write once when the first attempt times out
Avoid:
- Restating syntax
- Vague notes like "does stuff"
- Tagging every trivial line
3) System metadata
Create/update .dive/overview.md at the project root.
Required structure:
# System Overview
<brief system description>
## Components
- **<Component>** - <responsibility> -> <path>
## Relationships
- <Component A> -> <Component B>: <how they interact>
4) Module metadata
Create/update .dive/modules/<module>.md for modules affected by your changes.
Required structure:
# <Module> Module
<module purpose>
## Files
- `<relative/path>` - <file responsibility>
## Relationships
- <file A> -> <file B>: <dependency or call flow>
Operating Rules
- Keep paths project-relative (for example
src/auth/jwt.rs). - Update metadata incrementally when behavior changes.
- Preserve existing useful entries; refine instead of replacing wholesale.
- Prefer directional relationships (
A -> BorA <- B) with short context. - If
.dive/does not exist, create it withoverview.mdandmodules/. - If uncertain, write conservative descriptions and avoid guessing internals.
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.
- 2mo ago First seen · 122 lines · 26 tokens per session scan A b8eb2ba972f5
dive-tag is a skill published in the GitHub repository iantbutler01/code_diver (76 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 26 tokens to every session and 787 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.
dive-tag compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| dive-tagiantbutler01/code_diver | Skill | 76 | 7mo ago | Apache-2.0 | A | 26 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |