update-public-docs

A documentation maintenance tool that compares public API reference pages with the Python source code that defines the API. It updates missing or outdated documentation.

In plain words
What is it for?
Use it to refresh public API references, schemas, configuration docs, concepts, setup guides, and examples after Python code changes.
Why use it?
It reduces drift between code and documentation, so users are less likely to follow instructions for an API that has changed.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/reflexioai/claude-smart/update-public-docs
Any agent
npx skills add ReflexioAI/claude-smart --skill update-public-docs
Clone the repo
git clone --depth 1 https://github.com/ReflexioAI/claude-smart

Made for: Claude Code, Codex.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 825 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00057 $0.00825
Opus 5 $0.00028 $0.00413
Sonnet 5 $0.00011 $0.00165
Haiku 4.5 $0.00006 $0.00082

Measured 2d ago against content hash 44f5aba9a3a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update-public-docs 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 2d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

.agents/skills/update-public-docs/SKILL.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Public Docs

Keep the public documentation at reflexio/public_docs/ in sync with the Python source code (client library, schemas, config models).

Source Files (authoritative)

Read these files to understand the current API surface:

  • reflexio/reflexio_client/reflexio/client.py — All public client methods (defines what's client-facing)
  • reflexio/reflexio_commons/reflexio_commons/api_schema/service_schemas.py — Data models, enums, request/response schemas
  • reflexio/reflexio_commons/reflexio_commons/api_schema/retriever_schema.py — Search/get request/response models
  • reflexio/reflexio_commons/reflexio_commons/config_schema.py — Configuration models

Documentation Files (to update)

Read all MDX docs under reflexio/public_docs/content/docs/:

  • api-reference/client-*.mdx — Client method documentation
  • api-reference/schemas-*.mdx — Schema/model documentation
  • concepts/ — Core concept pages
  • getting-started/ — Quickstart and setup guides
  • examples/ — Usage examples

Workflow

Step 1: Read All Sources

Read every source file listed above. Extract:

  • All public methods from ReflexioClient (name, parameters with types/defaults, return type, docstring)
  • All public Pydantic models used by those methods (field name, type, required/optional, default, description)
  • All enum classes and their values
  • All config model fields

Step 2: Read All Documentation

Read every MDX file under reflexio/public_docs/content/docs/.

Step 3: Compare and Update

For each doc category, compare source against docs and fix discrepancies:

Client methods (client-*.mdx):

  • Every public method in client.py must be documented
  • Parameters: correct name, type, required/optional, default value
  • Return type and response schema must match
  • Remove docs for methods that no longer exist

Schema docs (schemas-*.mdx):

  • Every field in each Pydantic model must appear in the documentation tables
  • Field name, type, required/optional, default, and description must match source
  • Remove docs for models/fields that no longer exist

Read the full file on GitHub · 99 lines

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. 2d ago First seen · 99 lines · 57 tokens per session scan A 44f5aba9a3a0

Subscribe to this mod's changes

update-public-docs is a skill published in the GitHub repository ReflexioAI/claude-smart (774 stars, last pushed 4d ago), licensed Apache-2.0. It adds 57 tokens to every session and 825 once invoked, about $0.0003 per session on Opus 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.