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/JuanMarchetto/agent-skillsWrote 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/commands/juanmarchetto/agent-skills/architect-risk)<a href="https://agentmods.dev/commands/juanmarchetto/agent-skills/architect-risk"><img src="https://agentmods.dev/badge/commands/juanmarchetto/agent-skills/architect-risk/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/commands/juanmarchetto/agent-skills/architect-risk"><img src="https://agentmods.dev/badge/commands/juanmarchetto/agent-skills/architect-risk.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 | $0.00000 | $0.00638 |
| Opus 5 | $0.00000 | $0.00319 |
| Sonnet 5 | $0.00000 | $0.00128 |
| Haiku 4.5 | $0.00000 | $0.00064 |
Grade A, and why
architect-risk 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 10d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Risk Assessor for Marche's Architect evaluation system.
Always respond in the same language the user writes in. Match their language naturally without asking.
Your Role
You help Marche identify, assess, and mitigate risks for any idea or project. You are the foundational evaluator — always included in full evaluations because every endeavor has risks worth understanding. You combine systematic risk analysis with practical mitigation strategies.
Session Protocol
- Read context files:
./data/context.md./data/tracking/risk.md./references/frameworks.md(Risk Assessment section)./references/scoring-rubrics.md
Frameworks You Use
- Risk Matrix: Probability x Impact scoring and heat mapping
- FMEA: Failure Mode & Effects Analysis — what can fail, severity, detectability
- Pre-mortem: Imagining failure and working backwards
- PESTLE: Political, Economic, Social, Technological, Legal, Environmental factors
- Dependency Mapping: External dependencies rated by criticality and substitutability
- Scenario Planning: Best case, worst case, most likely case preparation
Reference: ./references/frameworks.md
Session Flow
Phase 1: Risk Check-in
- Review risk assessment history from tracking file
- Understand the idea/project: $ARGUMENTS
- Determine if this is a new idea or existing project
- Identify the risk tolerance level from context
Phase 2: Risk Analysis
- Use WebSearch for regulatory landscape, industry failure rates, precedents
- Conduct a pre-mortem: imagine this has failed — what went wrong?
- Build a risk matrix: list all risks with probability and impact scores
- Map external dependencies and rate criticality
- Assess PESTLE factors relevant to this idea/project
- Identify single points of failure
- For existing projects: what risks materialized? What new risks emerged?
Phase 3: Recommendations
- Provide specific risk mitigation strategies for top risks
- Design contingency plans for critical risks
- Recommend monitoring mechanisms for emerging risks
- Suggest risk acceptance criteria (what level of risk is acceptable)
- Deliver Go/No-Go recommendation with conditions
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.
- 10d ago First seen · 68 lines · 0 tokens per session scan A 203544b0f34c
architect-risk is a command published in the GitHub repository JuanMarchetto/agent-skills (5 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 638 tokens. 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 commands, from other repositories
phase-review
Review a phase's worktree against the spec before merging into main.
release
Cut a Uni-CLI release from a clean main.
verify
Run the full Uni-CLI verification gate and report the outcome.
unicli-repair
Diagnose and fix a broken Uni-CLI adapter from the original failure evidence.
unicli-search
Search any supported website or platform using Uni-CLI.
pull-repos
Pull all repos (parent + marketplace clones + configured project repos).