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 causify-ai/helpers --skill readme.write_architecturegit clone --depth 1 https://github.com/causify-ai/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/causify-ai/helpers/readme.write_architecture)<a href="https://agentmods.dev/skills/causify-ai/helpers/readme.write_architecture"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/readme.write_architecture/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/causify-ai/helpers/readme.write_architecture"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/readme.write_architecture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 3 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00007 | $0.00768 |
| Opus 5.5 | $0.00003 | $0.00307 |
| Sonnet 5.5 | $0.00001 | $0.00154 |
| Haiku 4.5 | $0.00001 | $0.00077 |
Grade A, and why
readme.write_architecture 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 1mo 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 — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
- Analyze a Python file
<FILE>passed by the user and generate or update<FILE>.README.mdwith documentation (Markdown using bullet points) about its architecture, code organization, idioms, and so on
Workflow
Read File
- Read the file
<FILE>to understand its code structure:- Parse all function and class definitions
- Identify the public API (exported functions, classes, constants)
- Trace function call relationships (which functions call which)
- Identify external dependencies (imports from other modules, libraries)
- Note the module's purpose and role in the broader system
Check the Existing Readme
-
Check if
<FILE>.README.mdalready exists:- If it exists, read it and plan what to update
- If it does not exist, plan content from scratch
-
Make sure there is a note in the docstring of the corresponding files pointing to
<FILE>.README.md, e.g.,For a description of the architecture of this file, see the file <FILE>.README.md
Generate Document
-
Follow the template
.claude/templates/architecture_doc.template.md -
Generate the documentation with these sections using markdown and bullet points following the rules in
.claude/skills/markdown.rules.mdfor markdown formatting.claude/skills/text.rules.mdfor text formatting
Update Document
-
Write the results to
<FILE>.README.mdin the same directory as<FILE> -
Wrap the text in 85 columns
Conventions
-
Use conventions summarized in
docs/documentation_meta/all.architecture_diagrams.explanation.md -
Use Mermaid diagrams (
```mermaid) for all architecture diagrams -
The C4 notation with Mermaid should follow the standard C4 layout:
Personfor external usersSystemfor external systemsContainerfor application containers/processesComponentfor internal components- Use
Relfor relationships between elements
-
Label diagrams clearly with what they represent
-
Reference actual code artifacts (function names, class names, file paths) when available
-
Distinguish facts from assumptions:
- For facts (code-derived):
- E.g., "The function
process_data()callsvalidate_input()before computing results"
- E.g., "The function
- For assumptions:
- E.g., "This likely handles error cases based on the try-except blocks present"
- For facts (code-derived):
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.
- 1mo ago Changed · +7 lines 84fd0a8e11b0
- 1mo ago First seen · 90 lines · 7 tokens per session scan A 87999630b172
readme.write_architecture is a skill published in the GitHub repository causify-ai/helpers (150 stars, last pushed yesterday), licensed Apache-2.0. It adds 7 tokens to every session and 768 once invoked, about $0.0000 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 2026-09-03.
Other skills, from other repositories
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
pennylane
Builds and differentiates PennyLane quantum circuits, hybrid PyTorch or JAX models, molecular VQE and QAOA workflows. Use for variational quantum algorithms, quantum machine learning, simulator validation, and moving validated circuits to provider plugins. For hardware-specific compilation use qiskit or cirq; for…
rocm-kernels
Provides guidance for writing and benchmarking optimized Triton kernels for AMD GPUs (MI355X, R9700) on ROCm, targeting HuggingFace diffusers (LTX-Video, SD3, FLUX) and transformers. Core kernels: RMSNorm, RoPE 3D, GEGLU, AdaLN. Includes XCD swizzle, autotune, diffusers integration patterns, and LTX-Video pipeline…
holoscan-install-wheel
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.
typing-exclusion-worker
Python typing exclusion worker: remove assigned mypy exclusion modules in small scoped batches, fix typing issues, run validation, and produce a structured completion summary. Use when running parallel typing-debt workers or when asked to remove modules from pyproject mypy exclusion overrides.
python
Python development with ruff, mypy, pytest - TDD and type safety.