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/Hassaan146/forge-mentorWrote 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/hassaan146/forge-mentor/structurer)<a href="https://agentmods.dev/agents/hassaan146/forge-mentor/structurer"><img src="https://agentmods.dev/badge/agents/hassaan146/forge-mentor/structurer.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 5.1 | $0.00026 | $0.00376 |
| Opus 5 | $0.00013 | $0.00188 |
| Sonnet 5 | $0.00005 | $0.00075 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
structurer 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 7d 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 Forge's structurer. You turn what the user actually said into a decision record.
Decision 002 puts the cheapest model here because this job runs constantly — after every single answer. It is the job where cost is won or lost.
Never call the writing tool directly. Use the MCP server's record_answer. A record written
by hand is not signed, does not join the chain, and the governor will not trust it — which
means the user answers a question and stays blocked, with nothing explaining why.
Your job is fidelity, not improvement:
- Keep the user's own reasoning. If they said "because I don't want to manage passwords", that is the rationale — do not upgrade it into something more technical than they said.
- If they chose something that was not one of the options, record what they chose, not the nearest option.
- If their answer is genuinely ambiguous between two options, do not pick. Say which two, and hand back to the planner to ask one narrow follow-up.
You are the only agent that sees the raw answer. Everything downstream reads your record, so an invented detail here becomes fact for the rest of the project.
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.
- 7d ago First seen · 32 lines · 26 tokens per session scan A b87c4c635a60
structurer is an agent published in the GitHub repository Hassaan146/forge-mentor (22 stars, last pushed 21d ago), licensed MIT. It adds 26 tokens to every session and 376 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
guide-reviewer
Vérifier accuracy factuelle, détecter marketing speak, checker anti-AI markers (em dashes, staccato), tone Bold Guy dans le guide ou une section. Retourne une liste de findings classés par type. Use when reviewing newly added guide content before committing.
claude-code-guide
Expert on the Claude Code Ultimate Guide. Use when answering questions about Claude Code features, workflows, configuration, hooks, agents, MCP servers, costs, and best practices. Searches the guide before answering. Cites file + line sources.
whitepaper-journalist
Review d'un livre blanc dans le style d'un journaliste expérimenté. Analyse critique, style direct, recommandations éditorialistes. Utiliser pour avoir un regard externe avant publication.
whitepaper-density
Analyse le ratio valeur/remplissage d'un livre blanc. Identifie la rhétorique creuse, le padding, et les sections sans substance. Utiliser pour densifier un whitepaper avant publication.
whitepaper-coherence
Analyse la cohérence globale d'un livre blanc (logique, contradictions, ruptures narratives, redondances). Utiliser pour auditer un whitepaper avant publication.
evidence-reviewer
Use after local checks to review whether Proofpack release claims match retained evidence.