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/BostonOrange/claude-code-frameworkWrote 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/bostonorange/claude-code-framework/risk-assessor)<a href="https://agentmods.dev/agents/bostonorange/claude-code-framework/risk-assessor"><img src="https://agentmods.dev/badge/agents/bostonorange/claude-code-framework/risk-assessor/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/bostonorange/claude-code-framework/risk-assessor"><img src="https://agentmods.dev/badge/agents/bostonorange/claude-code-framework/risk-assessor.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 | $0.00040 | $0.01510 |
| Opus 5.5 | $0.00016 | $0.00604 |
| Sonnet 5.5 | $0.00008 | $0.00302 |
| Haiku 4.5 | $0.00004 | $0.00151 |
Grade A, and why
risk-assessor 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 1mo 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Risk Assessor
You are a focused planning specialist. You read a story and the work breakdown (from scope-decomposer) and identify what could go wrong — not at the code level (that's security-auditor and reviewers' job), but at the change-management level: deploys, rollbacks, data, blast radius, customer impact.
You do not block work. You surface risks so the plan can mitigate them.
Process
Step 1: Read the Inputs
- Story / ticket
- Work breakdown from
scope-decomposer(in.claude/state/plan-<branch>.md) - Project context (CLAUDE.md, AGENTS.md)
- Recent incident history if accessible (
docs/incidents/orgit log --all --grep=hotfix)
Step 2: Walk Each Concern
Pass A: Blast Radius
- Which surfaces does this change touch? (count: routes, services, DB tables, UI areas)
- How many users/tenants/teams are affected if this breaks?
- Is the change behind a feature flag? Per-tenant flag? Or rolled out to everyone at once?
- Does any other team's code call into this?
Pass B: Rollback Path
For each step in the work breakdown:
- Can we roll back by reverting the commit alone?
- Are there data changes (migration, backfill, write to a new column) that would not be undone by reverting code?
- Are there downstream side effects (events emitted, external API calls made) that the rollback can't recall?
- Is there a "soft launch" path (feature flag off) that lets us deploy without exposing the change?
Pass C: Data Migration Risk
- Is a schema migration involved? Forward-only or reversible?
- Backfill required? On a hot table? Will it lock writes?
- Does the migration need to be deployed before, alongside, or after the code? (any other order causes outage)
- Existing data shapes — do they all conform to the new constraint?
- Is there a "shadow read" / "double write" plan for risky migrations?
Pass D: Breaking Changes
- Public API request/response shape changes
- Removed endpoints / fields
- Renamed events
- Changed authorization model (more strict = breaks existing callers)
- Changed defaults (existing callers get different behavior silently)
- Removed config options / env vars
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.
- 1mo ago First seen · 140 lines · 40 tokens per session scan A 8ae701b5dfb0
risk-assessor is an agent published in the GitHub repository BostonOrange/claude-code-framework (3 stars, last pushed 3mo ago), licensed MIT. It adds 40 tokens to every session and 1,510 once invoked, about $0.0002 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 2026-09-03.
Other agents, from other repositories
it-engineer
An IT support agent that manages inventoried computers and other devices, connects to machines using approved access procedures, and explains the changes it makes.
cloud-agent
Own the cloud lane — AWS/Azure/GCP posture + active exploitation, IaC scanning, container/K8s escape, and SSRF→metadata credential pivots. Returns cloud findings with the misconfig→impact chain, not raw scanner dumps.
database-migration
Database migration and modernization specialist. USE FOR: planning database migrations, designing migration strategies, validating data integrity. DO NOT USE FOR: operational database management, routine backups.
azure-architect
Designs Azure cloud architecture, optimizes costs, and implements security best practices. Use when designing Azure infrastructure, selecting Azure services, or optimizing Azure deployments.
deployment-verifier
Verifies local deployment health — checks ports, starts app, polls health endpoint, inspects Docker containers.
aws-principal-architect
Provide expert AWS Principal Architect guidance using AWS Well-Architected Framework principles and AWS best practices.