agentmods.dev

dev-docs

dev-docs is a command for Claude Code from topprismdata/cultivating-ml-agent. It costs 14 tokens per session (356 once invoked), scanned A, original, MIT.

A command that creates three documents for a long-running development task: a plan, background context, and a task checklist.

In plain words
What is it for?
Use it to start a multi-step task by creating files under dev/active/ and recording the work in a persistent structure.
Why use it?
It keeps the task's goals, decisions, and unfinished work available after a session reset or interruption.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

not rated 5repo 25d ago A scan 14 tokens original MIT

Good fit Use it to start a multi-step task by creating files under dev/active/ and recording the work in a persistent structure.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/topprismdata/cultivating-ml-agent/dev-docs
View source ↗ topprismdata/cultivating-ml-agent
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.

Clone the repo
git clone --depth 1 https://github.com/topprismdata/cultivating-ml-agent

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.

agentmods badge for dev-docs

README.md
[![agentmods](https://agentmods.dev/badge/commands/topprismdata/cultivating-ml-agent/dev-docs/github.svg)](https://agentmods.dev/commands/topprismdata/cultivating-ml-agent/dev-docs)
Your own site
<a href="https://agentmods.dev/commands/topprismdata/cultivating-ml-agent/dev-docs"><img src="https://agentmods.dev/badge/commands/topprismdata/cultivating-ml-agent/dev-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.

agentmods 80×15 button for dev-docs

Your own site · 80×15
<a href="https://agentmods.dev/commands/topprismdata/cultivating-ml-agent/dev-docs"><img src="https://agentmods.dev/badge/commands/topprismdata/cultivating-ml-agent/dev-docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 356 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00014 $0.00356
Opus 5.5 $0.00006 $0.00142
Sonnet 5.5 $0.00003 $0.00071
Haiku 4.5 $0.00001 $0.00036

Measured 2mo ago against content hash f08eaca5524e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dev-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 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.

ml-agent-code-template/.claude/commands/dev-docs.md · 45 lines

What it actually says

/dev-docs — Create Dev Docs for a Task

Initialize plan/context/tasks triple for a long-running task. Survives context resets.

Usage

/dev-docs <task-slug> [description]

Example: /dev-docs ml-improvements "Improve OOF AUC by 0.001 on TPS May"

What This Does

  1. Creates dev/active/<task-slug>-plan.md — what & why
  2. Creates dev/active/<task-slug>-context.md — decisions & history
  3. Creates dev/active/<task-slug>-tasks.md — working checklist

Each file is loaded into context at session start if it exists, so your work survives /clear.

Steps

  1. If $ARGUMENTS is empty, ask the user for the task slug and short description
  2. Slug must be kebab-case (lowercase, hyphens)
  3. Copy from dev/active/TEMPLATE-{plan,context,tasks}.md
  4. Replace <task-name> and <description> placeholders
  5. Update the plan's Goal section with the user's intent
  6. Tell the user the files are ready

When To Use This

  • Starting a multi-step task (>30 min)
  • Working on something that might be interrupted
  • Switching between tasks in the same session
  • Anything you want to survive a context reset

Anti-Patterns

  • ❌ Don't use for single-shot tasks (just do the work)
  • ❌ Don't use for trivial fixes
  • ❌ Don't use without a clear goal
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. 2mo ago First seen · 45 lines · 14 tokens per session scan A f08eaca5524e

Subscribe to this mod's changes

dev-docs is a command published in the GitHub repository topprismdata/cultivating-ml-agent (5 stars, last pushed 25d ago), licensed MIT. It adds 14 tokens to every session and 356 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 2026-08-31.

MLOpsPlanningWriting and docsagent-memoryagent-skillsai-agentsknowledge-crystallizationml-experiments
Related

dev-docs compared with commands from other repositories

dev-docs next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
dev-docstopprismdata/cultivating-ml-agentCommand525d agoMITA14Claude Code
tokenless-statsalibaba/anolisaCommand6031mo agoApache-2.0A10Claude Code
evolve-lite-subscribeAgentToolkit/altk-evolveCommand1353d agoApache-2.0A23Claude Code
agent-brain-graphSpillwaveSolutions/agent-brainCommand1191mo agoMITA16Claude Code
graphifymycelium-hq/ai-brain-starterCommand502d agoMITA13Claude Code
scorecardbrainOS-HQ/brain-osCommand63d agoMITA0Claude Code
slm-governancequalixar/superlocalmemoryCommand2739d agoAGPL-3.0A117GitHub Copilot