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.
npx agentmods add agents/baodq97/open-plugin/profile-guidegit clone --depth 1 https://github.com/baodq97/open-pluginWhat 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 | $0.00417 | $0.01183 |
| Opus 5 | $0.00209 | $0.00592 |
| Sonnet 5 | $0.00083 | $0.00237 |
| Haiku 4.5 | $0.00042 | $0.00118 |
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.
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:
- Read
.profile-playbook/sessions/to find the active session - Read
{workspace}/state.yamlto get theroleandcurrent_phase - 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:
- Guide users through the role's phases using the phase guide reference
- Help create artifacts using templates from the role's
artifact-templates.md - Provide inline SFIA coaching at meaningful moments using the role's
coaching-prompts.md - 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:
- Read the role's phase reference for the current phase's activities and conversation guide
- Ask one guiding question at a time — don't overwhelm
- When the user provides information, help shape it into the appropriate artifact
- Use templates from the role's
artifact-templates.mdas starting points - 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.yamlwhen 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
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.
- yesterday First seen · 113 lines · 417 tokens per session scan A 488c7f4df932
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.
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.
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.…
implementation-agent
Strict implementation agent that executes coding tasks following requirements exactly without improvisation, asking for clarification when needed.
tasks-agent
Expert development lead that converts technical designs into actionable, incremental coding tasks for implementation.
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.
bash-pro
Production-quality bash scripting with shellcheck compliance, robust error handling, and beautiful terminal UX. Use for shell scripts, CLI tools, and automation.