agentmods.dev

help

A command that explains the aidoc-flow plugin's eight-step Spec-Driven Development process and lists its main entry points. Spec-Driven Development means writing and checking project documents before implementation.

In plain words
What is it for?
It shows the document flow from business requirements to an implementation plan and code, points users to the routing skill, and identifies commands for starting or setting up a project.
Why use it?
It gives first-time users a starting point when the plugin's many skills, agents, and commands are difficult to navigate.

Command

17 2d ago A scan 31 tokens original MIT
View the source file vladm3105/aidoc-flow-framework
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 commands/vladm3105/aidoc-flow-framework/help
Clone the repo
git clone --depth 1 https://github.com/vladm3105/aidoc-flow-framework
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 929 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 $0.00031 $0.00929
Opus 5 $0.00015 $0.00464
Sonnet 5 $0.00006 $0.00186
Haiku 4.5 $0.00003 $0.00093

Measured 2d ago against content hash 26b296ba872a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

help 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.

platforms/claude-code-plugin/commands/help.md · 97 lines

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.

Help

Orient a first-time (or returning) user in the plugin. With 50+ skills, 11 agents, and 12 commands installed, the user needs a single screen that tells them: what the plugin does, where to start, and what's available.

This command does not orchestrate skills. The doc-flow skill is the orchestrator-of-record — it routes intent to the right skill and reports current position. /aidoc-flow:help is one level above that: it points users at doc-flow.

Instructions

  1. Print the elevator line (one paragraph):

    aidoc-flow is a Spec-Driven Development (SDD) workflow for Claude Code.
It drives a project from a Business Requirements Document down to an
implementation plan through eight traceable layers:

    BRD (1) → PRD (2) → EARS (3) → BDD (4) → ADR (5) → SPEC (6) → TDD (7) → IPLAN (8) → Code

Each layer is a SKILL. Run the skill, audit the output, fix it, promote
to the next layer.

  2. Top entry skills — print three lines, the same three the README Quickstart promotes:

    • doc-flow — "which skill do I need?" — start here when unsure
    • project-init — scaffold the docs/ layer tree for a new project
    • doc-brd-autopilot — draft the first layer (BRD) end-to-end

  3. Full command index — enumerate every file under ${CLAUDE_PLUGIN_ROOT}/commands/*.md, reading the title and description from each frontmatter block. Render as a grouped table; use the tags field to group (meta | workflow | lifecycle | config | utility). For each command print /aidoc-flow:<filename-without-md> and the description. Do not invent commands — only enumerate what's on disk.

    Commands

Meta
  /aidoc-flow:about         — show plugin/spec version, license, repo
  /aidoc-flow:help          — this command
  /aidoc-flow:bug-report    — file a bug with prefilled version stamp
  /aidoc-flow:contact-us    — contact channels
  /aidoc-flow:feedback      — share what worked / didn't / what to change

Workflow
  /aidoc-flow:status        — per-layer state of the current project
  /aidoc-flow:next          — one concrete next action

Lifecycle
  /aidoc-flow:uninstall     — guided exit
  /aidoc-flow:save-plan     — save the current session's plan to disk

Config
  /aidoc-flow:configure     — bulk editor for .claude/aidoc-flow.config.yaml
  /aidoc-flow:budget        — effort knob (advisory — see caveat in command)
  /aidoc-flow:model         — recommended model per layer (advisory)

Read the full file on GitHub · 97 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 · 97 lines · 31 tokens per session scan A 26b296ba872a

Subscribe to this mod's changes

help is a command published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed 2d ago), licensed MIT. It adds 31 tokens to every session and 929 once invoked, about $0.0002 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 2026-08-31.

activemeta
Related

Other commands, from other repositories

create-command

Create a new obsidian-second-brain command via interview - zero markdown editing required.

eugeniughelbur/obsidian-second-brain · 16 tokens

obsidian-health

Run a vault health check - grouped by severity, detects contradictions, concept gaps, stale claims, and structural issues.

eugeniughelbur/obsidian-second-brain · 22 tokens

obsidian-visualize

Generate a visual canvas map of your vault - see the shape of your second brain and how knowledge connects.

eugeniughelbur/obsidian-second-brain · 20 tokens

obsidian-architect

Scan a codebase and write a maintained set of architecture notes into the vault - overview, per-module notes, key decisions. Re-run to refresh without clobbering your edits.

eugeniughelbur/obsidian-second-brain · 36 tokens

obsidian-export

Export a clean structured snapshot of the vault that any agent or tool can consume - flat JSON, markdown index, or an OKF (Open Knowledge Format) bundle.

eugeniughelbur/obsidian-second-brain · 32 tokens

obsidian-retrieval-eval

Measure how well vault search finds the right note for a natural-language question - recall@k and MRR, with the concrete failures.

eugeniughelbur/obsidian-second-brain · 26 tokens