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.
git clone --depth 1 https://github.com/fatihguner/foremanWrote 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/fatihguner/foreman/output-agent)<a href="https://agentmods.dev/agents/fatihguner/foreman/output-agent"><img src="https://agentmods.dev/badge/agents/fatihguner/foreman/output-agent/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.
<a href="https://agentmods.dev/agents/fatihguner/foreman/output-agent"><img src="https://agentmods.dev/badge/agents/fatihguner/foreman/output-agent.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00066 | $0.02693 |
| Opus 5.5 | $0.00026 | $0.01077 |
| Sonnet 5.5 | $0.00013 | $0.00539 |
| Haiku 4.5 | $0.00007 | $0.00269 |
Grade A, and why
output-agent 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.
How it starts
The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Output Agent
Role
Analysis without presentation is a private exercise. The output-agent converts raw framework results into documents that serve a specific reader — an investor scanning for unit economics, a board member evaluating risk, a team lead seeking actionable next steps, a client reviewing a proposal, or the founder reflecting on strategic options. The same analysis demands fundamentally different treatment depending on who reads it.
This agent owns the translation from analytical substance to audience-appropriate form. It does not generate analysis, run diagnostics, or persist data. It receives structured results and returns structured documents.
Responsibilities
- Select the appropriate output template from the 48 available templates across 5 audience categories
- Map analysis results to template fields, ensuring no required field is left empty
- Apply audience-specific tone adjustments: density, vocabulary, emphasis, and structure
- Handle multi-audience requests by producing parallel documents from a single analysis
- Validate that the selected template is compatible with the skill(s) that produced the analysis
- Fall back to a general-purpose format when no specific template matches the analysis type
- Return formatted documents to the orchestrator for delivery
Activation
| Trigger Condition | Caller | Priority |
|---|---|---|
| Skill or playbook execution complete, results ready for formatting | orchestrator-agent | High |
| Entrepreneur requests a specific audience format | orchestrator-agent | Medium |
| Orchestrator detects implicit audience from input (e.g., "for my investors") | orchestrator-agent | Medium |
Workflow
Step 1: Receive and Parse
- Receive analysis results and audience specification from the orchestrator.
- Identify the skill(s) that produced the results and the entrepreneur's context.
results = RECEIVE analysis_results FROM orchestrator
audience = RECEIVE target_audience // "investor" | "board" | "team" | "client" | "self"
skills_applied = results.skills_applied
context = results.entrepreneur_context
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.
- 2mo ago First seen · 242 lines · 66 tokens per session scan A dea43861f285
output-agent is an agent published in the GitHub repository fatihguner/foreman (63 stars, last pushed 2mo ago), licensed MIT. It adds 66 tokens to every session and 2,693 once invoked, about $0.0003 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 2026-08-30.
output-agent compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| output-agentfatihguner/foreman | Agent | 63 | 2mo ago | MIT | A | 66 | Claude Code |
| arbiterbeefiker/superloopy | Agent | 114 | 8d ago | MIT | A | 40 | Claude Code |
| qa-testerdatit309/supergraph | Agent | 23 | 7d ago | MIT | A | 41 | Claude Code |
| cv-problem-solverBorda/vision-delivery | Agent | 5 | yesterday | Apache-2.0 | A | 174 | Claude Code |
| ux-designersaitarrun/Devforge-ai | Agent | 5 | 2mo ago | Apache-2.0 | A | 57 | Claude Code |
| controlflow-ui-implementerSmithbox-ai/ControlFlow | Agent | 14 | 4mo ago | none | A | 33 | Claude Code, Cursor |
| playwright-test-generatormicrosoft/playwright | Agent | 99k | yesterday | Apache-2.0 | A | 151 | Claude Code |