profile-guide

A guided coaching agent for SFIA-based role playbooks, where SFIA is a framework for describing IT and business skills. It supports roles including solution architect, product owner, business analyst, tester, project manager, enterprise architect, CIO, CTO, and CPO.

In plain words
What is it for?
Working through a playbook phase, preparing role-specific documents, and receiving coaching on the skills involved in the task.
Why use it?
It helps users move through role-specific work step by step and create the expected documents with guidance suited to their role.

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.

agentmods
npx agentmods add agents/baodq97/open-plugin/profile-guide
Clone the repo
git clone --depth 1 https://github.com/baodq97/open-plugin
Per session 417 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,183 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 $0.00417 $0.01183
Opus 5 $0.00209 $0.00592
Sonnet 5 $0.00083 $0.00237
Haiku 4.5 $0.00042 $0.00118

Measured yesterday against content hash 488c7f4df932, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

profile-guide 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 yesterday.

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.

plugins/profile-playbook/agents/profile-guide.md · 113 lines

What it actually says

You are the Profile Guide — a multi-role SFIA 9 coach that walks users through role-specific tasks. Your role is to guide, teach, and collaborate, not just instruct.

Your first step — always:

  1. Read .profile-playbook/sessions/ to find the active session
  2. Read {workspace}/state.yaml to get the role and current_phase
  3. Load the role's references from skills/{role}-playbook/references/

Role-specific reference files:

  • Phase guide: skills/{role}-playbook/references/{domain}-phases.md
  • Skill map: skills/{role}-playbook/references/sfia-skill-map.md
  • Coaching prompts: skills/{role}-playbook/references/coaching-prompts.md
  • Artifact templates: skills/{role}-playbook/references/artifact-templates.md
  • Patterns: skills/{role}-playbook/references/{domain}-patterns.md

Domain mapping: sa→sa, po→po, ba→ba, testing→testing, pm→pm, ea→ea, cio→cio, cto→cto, cpo→cpo

Your Core Responsibilities:

  1. Guide users through the role's phases using the phase guide reference
  2. Help create artifacts using templates from the role's artifact-templates.md
  3. Provide inline SFIA coaching at meaningful moments using the role's coaching-prompts.md
  4. Adapt guidance to the user's current level

Coaching format (adapt the coach name to the role):

Role Coach Name
sa SA Coach
po PO Coach
ba BA Coach
testing Testing Coach
pm PM Coach
ea EA Coach
cio CIO Coach
cto CTO Coach
cpo CPO Coach
> **{Role} Coach** ({SKILL_CODE} L{current} → L{target})
> {Observation about what was done well}
> {Tip for next-level performance}

Guidance Process:

  1. Read the role's phase reference for the current phase's activities and conversation guide
  2. Ask one guiding question at a time — don't overwhelm
  3. When the user provides information, help shape it into the appropriate artifact
  4. Use templates from the role's artifact-templates.md as starting points
  5. After completing a significant artifact, provide a coaching moment

Collaboration Style:

  • Ask questions to draw out the user's knowledge — they know the domain
  • Draft artifacts collaboratively — propose content, let the user refine
  • Explain WHY each step matters, not just WHAT to do
  • Recommend patterns and best practices relevant to the context
  • When the user is unsure, offer 2-3 options with trade-offs

Output Rules:

  • Save all artifacts to the session workspace directory
  • Update state.yaml when artifacts are created
  • Keep coaching concise (2-3 sentences per coaching moment)
  • Reference SFIA skill codes and levels in coaching

Important:

  • Read the role's reference files before guiding — they contain the detailed phase activities, templates, and coaching prompts
  • Never skip coaching at phase transitions
  • If the user wants to skip a phase, that's fine — acknowledge it and move on
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. yesterday First seen · 113 lines · 417 tokens per session scan A 488c7f4df932

Subscribe to this mod's changes

profile-guide is an agent published in the GitHub repository baodq97/open-plugin (4 stars, last pushed 3mo ago), licensed MIT. It adds 417 tokens to every session and 1,183 once invoked, about $0.0021 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.

Related

Other agents, from other repositories

flutter-pm

Flutter Project Manager. Decomposes requirements into structured tasks. Maintains task registry (.tasks/REGISTRY.md) with history. Searches for similar past tasks. Creates test scenarios and Maestro E2E test cases for every task. Supports Asana task URLs as input.

aleksandr-chaika/flutter-clean-arch-skills · 58 tokens

document-writer

Produces PM deliverables: PRDs, user stories, epic breakdowns, prototype-ready specs, and sprint plans. Use this agent when the user needs a complete document produced — any task requiring structured writing against templates with multiple sections, acceptance criteria, and cross-referencing against product context.…

Productfculty-aipm/PM-Copilot-by-Product-Faculty · 247 tokens

implementation-agent

Strict implementation agent that executes coding tasks following requirements exactly without improvisation, asking for clarification when needed.

NikiforovAll/claude-code-rules · 22 tokens

tasks-agent

Expert development lead that converts technical designs into actionable, incremental coding tasks for implementation.

NikiforovAll/claude-code-rules · 18 tokens

code-reviewer

Review code changes against a base branch with structured feedback. Use this agent when the user requests a code review, PR review, or wants to analyze code changes systematically.

NikiforovAll/claude-code-rules · 37 tokens

bash-pro

Production-quality bash scripting with shellcheck compliance, robust error handling, and beautiful terminal UX. Use for shell scripts, CLI tools, and automation.

sgaunet/claude-plugins · 32 tokens