What is conditional_docs?

A task-based documentation router that tells an agent which project files to read first. It matches tasks such as new features, bug fixes, and chores to relevant planning documents.

Use it at the start of a task to choose the right planning, architecture, configuration, or specification files.

It avoids reading unrelated documentation and gives the agent the project context needed for the current kind of work.

How bredmond1019/claude-sdk-rs configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/bredmond1019/claude-sdk-rs/main/.claude/commands/conditional_docs.md

Clone the repo

git clone --depth 1 https://github.com/bredmond1019/claude-sdk-rs

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/conditional_docs/github.svg)](https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/conditional_docs)

Your own site

<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/conditional_docs"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/conditional_docs/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/bredmond1019/claude-sdk-rs/conditional_docs"><img src="https://agentmods.dev/badge/commands/bredmond1019/claude-sdk-rs/conditional_docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 660 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00660
Opus 5.5	$0.00000	$0.00264
Sonnet 5.5	$0.00000	$0.00132
Haiku 4.5	$0.00000	$0.00066

Measured 11d ago against content hash 9b53ae32f749, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

conditional_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 11d 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.

.claude/commands/conditional_docs.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/conditional_docs — Task-type documentation router

Routes the agent to the documentation most relevant to the current task type. Use this at the start of a task to avoid reading unrelated files. Takes an optional $ARGUMENTS describing what kind of task you are about to do.

Instructions

Read $ARGUMENTS. Match it to the closest category below and direct yourself (or the user) to read the listed files. If the argument is absent or does not match, use the default set.

new feature / feature

You are building something new — a capability, endpoint, or component that does not exist yet.

Read in this order:

planning/master-plan.md — understand the project's overall direction and where this feature fits.
planning/context.md — confirm the architectural constraints.
planning/harness.json — check validation commands and any stack-specific config.
The relevant spec in planning/<concept>/tasks.md if one already exists.

Then use /generate-tasks (or /plan) to plan the work before starting.

bug / fix / hotfix

You are fixing something broken.

Read in this order:

planning/context.md — orient to the codebase.
planning/harness.json — know the validation commands you will run after fixing.

Then:

If the fix touches one or two files with no new tests needed → use /patch.
If the fix is multi-file or requires new tests → use /sdlc-flow.

api / endpoint

You are adding or modifying an API endpoint.

Read in this order:

The project's CLAUDE.md — look for API conventions (naming, auth, error format).
planning/harness.json — check if there are API-specific validation checks.
docs/api-reference.md if it exists — avoid duplicating or breaking existing patterns.

test / testing

You are writing or running tests.

Read in this order:

planning/harness.json — validation.checks[] defines what the harness runs; understand the check kinds (command, baseline-diff, count-delta, etc.).
.claude/commands/e2e/README.md — available E2E test templates and how to use them.
The relevant spec's ## Validation Commands section if you are writing task-specific tests.

Read the full file on GitHub · 86 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.

11d ago First seen · 86 lines · 0 tokens per session scan A 9b53ae32f749

Subscribe to this mod's changes

conditional_docs is a command published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 660 tokens. 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 2026-10-26.

Debugging Planning Writing and docs

conditional_docs next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
conditional_docsbredmond1019/claude-sdk-rs	Command	23	1mo ago	Apache-2.0	A	0	Claude Code
qa-changesOpenHands/extensions	Command	176	yesterday	MIT	A	63	Claude Code
react-nativegetsentry/toolkit	Command	957	yesterday	none	A	0	Claude Code
auditar-cascadingluanpdd/kit-mcp	Command	5	4d ago	MIT	A	54	Claude Code
http-serviceMadAppGang/magus	Command	14	yesterday	MIT	A	27	Claude Code
doctordoncheli/don-cheli-sdd	Command	59	2mo ago	Apache-2.0	A	76	Claude Code
doctorfatihkan/badi	Command	7	1mo ago	MIT	A	0	Claude Code

claude-sdk-rs: Command for Claude Code

Borrowing it

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/conditional_docs — Task-type documentation router

Instructions

new feature / feature

bug / fix / hotfix

api / endpoint

test / testing

What this file has done since we first saw it

conditional_docs compared with commands from other repositories