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 gpsaggese/helpers --skill readme_file.explain_codegit clone --depth 1 https://github.com/gpsaggese/helpersWrote 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/gpsaggese/helpers/readme_file.explain_code)<a href="https://agentmods.dev/skills/gpsaggese/helpers/readme_file.explain_code"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/readme_file.explain_code/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/gpsaggese/helpers/readme_file.explain_code"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/readme_file.explain_code.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 | $0.00013 | $0.01642 |
| Opus 5.5 | $0.00005 | $0.00657 |
| Sonnet 5.5 | $0.00003 | $0.00328 |
| Haiku 4.5 | $0.00001 | $0.00164 |
Grade A, and why
readme_file.explain_code 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 yesterday.
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 — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
- Read the Python files passed by the user and write
explain_code.<descr>.md, documenting their classes, functions, interfaces, and relationships
Workflow
Read the Files
- Read every Python file
<FILE>passed by the user or referenced in the request
Generate the Document
- Write the file in the current directory as
explain_code.<descr>.md<descr>is a short slug, typically the source file's basename without extension (e.g.,batch_call_auctionforbatch_call_auction.py); use a combined slug for several files
- Say in the output file how it was generated, with this line right after the title:
- Generated by `.claude/skills/readme_file.explain_code/SKILL.md` - Include the five sections below, in this exact order
- Under each section, print one level-2 header (
##) per file read, using the same path used to read it (this disambiguates files with the same basename) - Omit a section, or a file's subsection within it, entirely if there is nothing
to report; never print an empty header or a placeholder bullet like
- - Print the result only to the file, not to the screen
Verify
- Follow the
# Verificationchecklist below before returning the result
File Description
-
Print a nested bullet list per file: its abstractions and functionalities
-
Order files by use relationship
- E.g., if file X is imported by Y, then X comes before Y in the list
-
E.g.,
- `batch_call_auction.py` - In-memory order book for a batch call auction - Queues buy/sell orders, buckets by capability tier - Clears each tier at a uniform price once per round - `passthrough_proxy.py` - LLM provider gateway - Routes a prompt to a registered provider - Times the call, estimates cost, and logs every request/response pair for later query
Class Description
-
For each file, print one bullet per class, with a description under 20 words
-
E.g.,
# Class Description ## `research/Noesis/batch_call_auction.py` - `Bid` - Buyer order: (tasks, min tier, max latency, min reliability, max price) - `Ask` - Seller order: (tasks, tier, typical latency/reliability, min price) - `Fill` - One matched buyer/seller trade at a tier's uniform clearing price - `TierClearResult` - Outcome of clearing one tier (price, fills, unfilled quantities) - `OrderBookStore` - Abstract pluggable storage backend for pending bids/asks ## <file.py> ...
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.
- yesterday First seen · 213 lines · 13 tokens per session scan A edd13a89cb37
readme_file.explain_code is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 13 tokens to every session and 1,642 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 2026-11-06.
readme_file.explain_code compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| readme_file.explain_codegpsaggese/helpers | Skill | 158 | today | Apache-2.0 | A | 13 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 56k | 5d ago | MIT | A | 44 | Claude Code |
| pennylaneK-Dense-AI/scientific-agent-skills | Skill | 56k | 5d ago | MIT | A | 74 | Claude Code |
| holoscan-install-wheelNVIDIA/skills | Skill | 3.9k | today | Apache-2.0 | A | 34 | Claude Code, Codex |
| future-self-liteTHU-MAIC/OpenMAIC | Skill | 43k | yesterday | MIT | A | 20 | Claude Code, Codex |
| rocm-kernelshuggingface/kernels | Skill | 783 | yesterday | Apache-2.0 | A | 93 | Claude Code |
| typing-exclusion-workergetsentry/skills | Skill | 1.1k | yesterday | Apache-2.0 | A | 57 | Claude Code |