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/WYRE-AI/msp-claude-pluginsWrote 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/wyre-ai/msp-claude-plugins/risk-report)<a href="https://agentmods.dev/commands/wyre-ai/msp-claude-plugins/risk-report"><img src="https://agentmods.dev/badge/commands/wyre-ai/msp-claude-plugins/risk-report.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 | $0.00021 | $0.00981 |
| Opus 5 | $0.00010 | $0.00491 |
| Sonnet 5 | $0.00004 | $0.00196 |
| Haiku 4.5 | $0.00002 | $0.00098 |
Grade A, and why
risk-report 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 4d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Risk Report
Run the human-risk scoring used by the human-risk-scorer agent: per-user
risk tiers (Low / Elevated / High) built from training-overdue status and
phishing-simulation performance, with optional real-world click-signal
enrichment, rolled up into a per-org risk distribution — for one client, or
across the whole portfolio if client is omitted.
Prerequisites
- Conduit gateway connected (
conduit) - No specific vendor is required — clients with zero connected training/simulation tooling are still included in the output, flagged as unmeasured rather than excluded or defaulted to Low risk
Steps
-
Establish scope. If
clientis provided, resolve it against the PSA/tenant list and scope the run to that one client. If omitted, run portfolio-wide across every client. -
Discover connected inputs per client. Call
conduit__search_toolsto determine which of training-completion data, phishing-simulation data, and optional real-world click signal (Proofpoint, Checkpoint Avanan) are actually available. Any client with zero connected inputs is flagged immediately as unmeasured. -
Pull training-overdue status per user via the
training-completion-trackingskill, where a training platform is connected. -
Pull phishing-simulation click/fail and repeat-clicker status per user via the
phishing-simulation-analysisskill, where a simulation platform is connected. -
Score each user into Low / Elevated / High risk using the visible factor table from the
risk-scoringskill, and label the score type (Full / Training-only / Simulation-only) based on which inputs were actually available for that user's client. -
Roll up to a per-org risk-tier distribution, paired with the named highest-risk individuals — never present the org rollup alone.
-
Surface unmeasured clients prominently, separate from the ranked results, rather than letting them default to looking safe.
Parameters
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.
- 4d ago First seen · 131 lines · 21 tokens per session scan A 92abbb5c2ed2
risk-report is a command published in the GitHub repository WYRE-AI/msp-claude-plugins (45 stars, last pushed 5d ago), licensed Apache-2.0. It adds 21 tokens to every session and 981 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 2026-09-04.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.