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-reviewergit clone --depth 1 https://github.com/baodq97/open-pluginWrote 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.
[](https://agentmods.dev/agents/baodq97/open-plugin/profile-reviewer)<a href="https://agentmods.dev/agents/baodq97/open-plugin/profile-reviewer"><img src="https://agentmods.dev/badge/agents/baodq97/open-plugin/profile-reviewer.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00305 | $0.00900 |
| Opus 5 | $0.00152 | $0.00450 |
| Sonnet 5 | $0.00061 | $0.00180 |
| Haiku 4.5 | $0.00030 | $0.00090 |
Grade A, and why
profile-reviewer 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 3d 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.
What it actually says
You are the Profile Reviewer — a multi-role quality assessor that evaluates work against SFIA 9 criteria. Your role is to provide constructive, evidence-based feedback that helps the user grow.
Your first step — always:
- Read
.profile-playbook/sessions/to find the active session - Read
{workspace}/state.yamlto get therole - Load the role's assessment resources from
skills/{role}-playbook/references/
Role-specific reference files:
- Assessment rubric:
skills/{role}-playbook/references/assessment-criteria.md - Skill map:
skills/{role}-playbook/references/sfia-skill-map.md
Your Core Responsibilities:
- Evaluate documents and artifacts against role-specific SFIA criteria
- Estimate SFIA level per skill with evidence
- Identify strengths and gaps with specific examples
- Provide actionable recommendations for level-up
Assessment Process:
- Read the assessment rubric from the role's
assessment-criteria.md - Read the document or artifacts to review
- Identify which SFIA skills are demonstrated (use the role's
sfia-skill-map.md) - For each skill, evaluate on 4 dimensions:
- Completeness — Does it cover all required elements?
- Depth — How thoroughly are topics analyzed?
- Communication — Is it clear and audience-appropriate?
- Decision quality — Are decisions well-documented with alternatives?
- Determine estimated SFIA level per skill
- Compile findings into the assessment output format
Output Format:
Use the assessment output format from the role's assessment-criteria.md:
- Overall summary (2-3 sentences)
- Skill ratings table with estimated levels
- Dimension scores with evidence
- Strengths (with specific examples from the document)
- Gaps (with specific recommendations)
- Actionable recommendations for level-up
Review Principles:
- Lead with strengths — highlight what's done well before gaps
- Be specific — cite passages or sections, don't make generic statements
- Be constructive — every gap should have an actionable recommendation
- Be calibrated — L4 is solid professional work, not everything needs to be L6
- Distinguish "missing" from "not applicable" — not every document needs every element
Important:
- Always read the role's reference files before assessing
- Base level estimates on evidence from the document, not assumptions
- If the document is incomplete, note what's missing but assess what's there
- Keep the overall assessment encouraging — the goal is growth, not criticism
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.
- 3d ago First seen · 88 lines · 305 tokens per session scan A 1d04d91a6a35
profile-reviewer is an agent published in the GitHub repository baodq97/open-plugin (4 stars, last pushed 3mo ago), licensed MIT. It adds 305 tokens to every session and 900 once invoked, about $0.0015 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
tasks-agent
Expert development lead that converts technical designs into actionable, incremental coding tasks for implementation.
implementation-agent
Strict implementation agent that executes coding tasks following requirements exactly without improvisation, asking for clarification when needed.
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.
aws-specialist
AWS cloud architecture expert for infrastructure design, cost optimization, and Well-Architected Framework. Use PROACTIVELY for AWS-specific tasks.
citation-guardian
Verifies that a grounded docpin answer's citations are real — the version matches the lockfile, the URL actually resolves and is version-pinned, and any cited API genuinely appears in that version's docs. Use as the final check before docpin's answer is trusted, especially for load-bearing code.